Search Results for author:
Found 348 papers, 188 papers with code
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
Learning Generalized Reactive Policies using Deep Neural Networks
We show that a deep neural network can be used to learn and represent a \emph{generalized reactive policy} (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances.
Latent Space Policies for Hierarchical Reinforcement Learning
In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating signals, each layer in our framework is trained to directly solve the task, but acquires a range of diverse strategies via a maximum entropy reinforcement learning objective.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Domain Randomization and Generative Models for Robotic Grasping
In this work, we explore a novel data generation pipeline for training a deep neural network to perform grasp planning that applies the idea of domain randomization to object synthesis.
Learning Robotic Assembly from CAD
We propose to leverage this prior knowledge by guiding RL along a geometric motion plan, calculated using the CAD data.
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
To mitigate this issue, we derive a bias-free action-dependent baseline for variance reduction which fully exploits the structural form of the stochastic policy itself and does not make any additional assumptions about the MDP.
Interpretable and Pedagogical Examples
Teachers intentionally pick the most informative examples to show their students.
A Berkeley View of Systems Challenges for AI
With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising and intelligent infrastructures, AI (Artificial Intelligence) has moved from research labs to production.
One-Shot Imitation Learning
A neural net is trained that takes as input one demonstration and the current state (which initially is the initial state of the other demonstration of the pair), and outputs an action with the goal that the resulting sequence of states and actions matches as closely as possible with the second demonstration.
Safer Classification by Synthesis
We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models.
Equivalence Between Policy Gradients and Soft Q-Learning
A partial explanation may be that $Q$-learning methods are secretly implementing policy gradient updates: we show that there is a precise equivalence between $Q$-learning and policy gradient methods in the setting of entropy-regularized reinforcement learning, that "soft" (entropy-regularized) $Q$-learning is exactly equivalent to a policy gradient method.
Inverse Reward Design
When designing the reward, we might think of some specific training scenarios, and make sure that the reward will lead to the right behavior in those scenarios.
UCB Exploration via Q-Ensembles
We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning.
Asymmetric Actor Critic for Image-Based Robot Learning
While several recent works have shown promising results in transferring policies trained in simulation to the real world, they often do not fully utilize the advantage of working with a simulator.
Reverse Curriculum Generation for Reinforcement Learning
The robot is trained in reverse, gradually learning to reach the goal from a set of start states increasingly far from the goal.
Mutual Alignment Transfer Learning
Training robots for operation in the real world is a complex, time consuming and potentially expensive task.
Prediction and Control with Temporal Segment Models
We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions.
The Off-Switch Game
We analyze a simple game between a human H and a robot R, where H can press R's off switch but R can disable the off switch.
Adapting Deep Visuomotor Representations with Weak Pairwise Constraints
We propose a novel, more powerful combination of both distribution and pairwise image alignment, and remove the requirement for expensive annotation by using weakly aligned pairs of images in the source and target domains.
Probabilistically Safe Policy Transfer
Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy.
Inverse Reinforcement Learning via Deep Gaussian Process
We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations.
Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration
In this paper, we describe an approach to learning from demonstration that can be used to train soft robotic hands to perform dexterous manipulation tasks.
Generalizing Skills with Semi-Supervised Reinforcement Learning
We evaluate our method on challenging tasks that require control directly from images, and show that our approach can improve the generalization of a learned deep neural network policy by using experience for which no reward function is available.
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures.
Deep Reinforcement Learning for Tensegrity Robot Locomotion
We evaluate our method with real-world and simulated experiments on the SUPERball tensegrity robot, showing that the learned policies generalize to changes in system parameters, unreliable sensor measurements, and variation in environmental conditions, including varied terrains and a range of different gravities.
Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation
Manipulation of deformable objects, such as ropes and cloth, is an important but challenging problem in robotics.
Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification.
PLATO: Policy Learning using Adaptive Trajectory Optimization
PLATO also maintains the MPC cost as an objective to avoid highly undesirable actions that would result from strictly following the learned policy before it has been fully trained.
Enabling Robots to Communicate their Objectives
We show that certain approximate-inference models lead to the robot generating example behaviors that better enable users to anticipate what it will do in novel situations.
Uncertainty-Aware Reinforcement Learning for Collision Avoidance
However, practical deployment of reinforcement learning methods must contend with the fact that the training process itself can be unsafe for the robot.
A K-fold Method for Baseline Estimation in Policy Gradient Algorithms
The high variance issue in unbiased policy-gradient methods such as VPG and REINFORCE is typically mitigated by adding a baseline.
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
Nevertheless, often the overall gist of what the policy does in simulation remains valid in the real world.
Reset-Free Guided Policy Search: Efficient Deep Reinforcement Learning with Stochastic Initial States
Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering.
Combinatorial Energy Learning for Image Segmentation
We introduce a new machine learning approach for image segmentation that uses a neural network to model the conditional energy of a segmentation given an image.
Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer
Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations.
One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors
One of the key challenges in applying reinforcement learning to complex robotic control tasks is the need to gather large amounts of experience in order to find an effective policy for the task at hand.
Model-based Reinforcement Learning
Model Predictive Control
+3
End-to-End Training of Deep Visuomotor Policies
Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control.
Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration
In this paper, we present a robotic model-based reinforcement learning method that combines ideas from model identification and model predictive control.
Model-based Reinforcement Learning
Model Predictive Control
+2
Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search
We propose to combine MPC with reinforcement learning in the framework of guided policy search, where MPC is used to generate data at training time, under full state observations provided by an instrumented training environment.
Learning Deep Neural Network Policies with Continuous Memory States
We evaluate our method on tasks involving continuous control in manipulation and navigation settings, and show that our method can learn complex policies that successfully complete a range of tasks that require memory.
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
By randomizing the dynamics of the simulator during training, we are able to develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained.
Robotics Systems and Control
Variational Option Discovery Algorithms
We explore methods for option discovery based on variational inference and make two algorithmic contributions.
Transfer Learning for Estimating Causal Effects using Neural Networks
We develop new algorithms for estimating heterogeneous treatment effects, combining recent developments in transfer learning for neural networks with insights from the causal inference literature.
One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
We consider the problem of learning multi-stage vision-based tasks on a real robot from a single video of a human performing the task, while leveraging demonstration data of subtasks with other objects.
Modular Architecture for StarCraft II with Deep Reinforcement Learning
We present a novel modular architecture for StarCraft II AI.
An Algorithmic Perspective on Imitation Learning
This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning.
The Importance of Sampling inMeta-Reinforcement Learning
Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
We present a policy search method that uses iteratively refitted local linear models to optimize trajectory distributions for large, continuous problems.
On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient
Likelihood ratio policy gradient methods have been some of the most successful reinforcement learning algorithms, especially for learning on physical systems.
Learning to Reinforcement Learn by Imitation
Meta-reinforcement learning aims to learn fast reinforcement learning (RL) procedures that can be applied to new tasks or environments.
Inferring Reward Functions from Demonstrators with Unknown Biases
Our goal is to infer reward functions from demonstrations.
Self-Supervised Learning of Object Motion Through Adversarial Video Prediction
In this paper, we study the problem of multi-step video prediction, where the goal is to predict a sequence of future frames conditioned on a short context.
Domain Randomization for Active Pose Estimation
In this work, we investigate how to improve the accuracy of domain randomization based pose estimation.
Towards Characterizing Divergence in Deep Q-Learning
Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation.
Guided Meta-Policy Search
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch.
Learning Robotic Manipulation through Visual Planning and Acting
We further demonstrate our approach on learning to imagine and execute in 3 environments, the final of which is deformable rope manipulation on a PR2 robot.
Learning latent state representation for speeding up exploration
In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore.
Sub-policy Adaptation for Hierarchical Reinforcement Learning
Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards.
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraught with specific assumptions, and instead use a purely data-driven approach.
BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks
The discrepancy between post-layout and schematic simulation results continues to widen in analog design due in part to the domination of layout parasitics.
Likelihood Contribution based Multi-scale Architecture for Generative Flows
Deep generative modeling using flows has gained popularity owing to the tractable exact log-likelihood estimation with efficient training and synthesis process.
Learning Contact-Rich Manipulation Skills with Guided Policy Search
Autonomous learning of object manipulation skills can enable robots to acquire rich behavioral repertoires that scale to the variety of objects found in the real world.
Robotics
Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control
We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training.
Learning Efficient Representation for Intrinsic Motivation
The core idea is to represent the relation between action sequences and future states using a stochastic dynamic model in latent space with a specific form.
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos
In this paper, we study how these challenges can be alleviated with an automated robotic learning framework, in which multi-stage tasks are defined simply by providing videos of a human demonstrator and then learned autonomously by the robot from raw image observations.
Natural Image Manipulation for Autoregressive Models Using Fisher Scores
Deep autoregressive models are one of the most powerful models that exist today which achieve state-of-the-art bits per dim.
Establishing Appropriate Trust via Critical States
In order to effectively interact with or supervise a robot, humans need to have an accurate mental model of its capabilities and how it acts.
Robotics
Hierarchical Variational Imitation Learning of Control Programs
Autonomous agents can learn by imitating teacher demonstrations of the intended behavior.
Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards
While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge.
Preventing Imitation Learning with Adversarial Policy Ensembles
To our knowledge, this is the first work regarding the protection of policies in Reinforcement Learning.
Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal.
GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction
In this work we present a new method of black-box optimization and constraint satisfaction.
The Limits and Potentials of Deep Learning for Robotics
In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning.
Robotics
Generalized Hindsight for Reinforcement Learning
Compared to standard relabeling techniques, Generalized Hindsight provides a substantially more efficient reuse of samples, which we empirically demonstrate on a suite of multi-task navigation and manipulation tasks.
Mutual Information Maximization for Robust Plannable Representations
The later, while they present low sample complexity, they learn latent spaces that need to reconstruct every single detail of the scene.
Model-Augmented Actor-Critic: Backpropagating through Paths
Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator to augment the data for policy optimization or value function learning.
Responsive Safety in Reinforcement Learning by PID Lagrangian Methods
Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior during agent training.
Efficient Empowerment Estimation for Unsupervised Stabilization
We demonstrate our solution for sample-based unsupervised stabilization on different dynamical control systems and show the advantages of our method by comparing it to the existing VLB approaches.
Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning
Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments.
Visual Imitation Made Easy
We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector.
Hierarchically Decoupled Morphological Transfer
Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning.
Responsive Safety in Reinforcement Learning
This intuition leads to our introduction of PID control for the Lagrange multiplier in constrained RL, which we cast as a dynamical system.
Planning to Explore via Latent Disagreement
To solve complex tasks, intelligent agents first need to explore their environments.
VideoGen: Generative Modeling of Videos using VQ-VAE and Transformers
We present VideoGen: a conceptually simple architecture for scaling likelihood based generative modeling to natural videos.
Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets
As it turns out, fine-tuning offline RL agents is a non-trivial challenge, due to distribution shift – the agent encounters out-of-distribution samples during online interaction, which may cause bootstrapping error in Q-learning and instability during fine-tuning.
Unsupervised Active Pre-Training for Reinforcement Learning
On DMControl suite, APT beats all baselines in terms of asymptotic performance and data efficiency and dramatically improves performance on tasks that are extremely difficult for training from scratch.
Robust Imitation via Decision-Time Planning
The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal.
R-LAtte: Attention Module for Visual Control via Reinforcement Learning
Attention mechanisms are generic inductive biases that have played a critical role in improving the state-of-the-art in supervised learning, unsupervised pre-training and generative modeling for multiple domains including vision, language and speech.
Weighted Bellman Backups for Improved Signal-to-Noise in Q-Updates
Furthermore, since our weighted Bellman backups rely on maintaining an ensemble, we investigate how weighted Bellman backups interact with other benefits previously derived from ensembles: (a) Bootstrap; (b) UCB Exploration.
Benefits of Assistance over Reward Learning
By merging reward learning and control, assistive agents can reason about the impact of control actions on reward learning, leading to several advantages over agents based on reward learning.
Compute- and Memory-Efficient Reinforcement Learning with Latent Experience Replay
In this paper, we present Latent Vector Experience Replay (LeVER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements without sacrificing the performance of RL agents.
Discrete Predictive Representation for Long-horizon Planning
Discrete representations have been key in enabling robots to plan at more abstract levels and solve temporally-extended tasks more efficiently for decades.
Learning Visual Robotic Control Efficiently with Contrastive Pre-training and Data Augmentation
We present Contrastive Pre-training and Data Augmentation for Efficient Robotic Learning (CoDER), a method that utilizes data augmentation and unsupervised learning to achieve sample-efficient training of real-robot arm policies from sparse rewards.
Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
Developing robust walking controllers for bipedal robots is a challenging endeavor.
GEM: Group Enhanced Model for Learning Dynamical Control Systems
In this work, we take advantage of these structures to build effective dynamical models that are amenable to sample-based learning.
Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL
When combined together, they substantially improve the performance and generalization of offline RL policies.
Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments
To showcase the benefits, we interfaced SCENIC to an existing RTS environment Google Research Football(GRF) simulator and introduced a benchmark consisting of 32 realistic scenarios, encoded in SCENIC, to train RL agents and testing their generalization capabilities.
The MineRL BASALT Competition on Learning from Human Feedback
Rather than training AI systems using a predefined reward function or using a labeled dataset with a predefined set of categories, we instead train the AI system using a learning signal derived from some form of human feedback, which can evolve over time as the understanding of the task changes, or as the capabilities of the AI system improve.
Playful Interactions for Representation Learning
In this work, we propose to use playful interactions in a self-supervised manner to learn visual representations for downstream tasks.
Skill Preferences: Learning to Extract and Execute Robotic Skills from Human Feedback
A promising approach to solving challenging long-horizon tasks has been to extract behavior priors (skills) by fitting generative models to large offline datasets of demonstrations.
APS: Active Pretraining with Successor Features
We introduce a new unsupervised pretraining objective for reinforcement learning.
Improving Long-Horizon Imitation Through Language Prediction
Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents.
Pretraining for Language Conditioned Imitation with Transformers
We study reinforcement learning (RL) agents which can utilize language inputs.
Autoregressive Latent Video Prediction with High-Fidelity Image Generator
Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics.
Semi-supervised Offline Reinforcement Learning with Pre-trained Decision Transformers
In this paper, we investigate how we can leverage large reward-free (i. e. task-agnostic) offline datasets of prior interactions to pre-train agents that can then be fine-tuned using a small reward-annotated dataset.
Towards More Generalizable One-shot Visual Imitation Learning
We then study the multi-task setting, where multi-task training is followed by (i) one-shot imitation on variations within the training tasks, (ii) one-shot imitation on new tasks, and (iii) fine-tuning on new tasks.
Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
Under the belief that $\beta$ is closely related to the (state dependent) model uncertainty, Entropy Regularized Q-Learning (EQL) further introduces a principled scheduling of $\beta$ by maintaining a collection of the model parameters that characterizes model uncertainty.
Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning
We show that a single generalist policy can perform in-hand manipulation of over 100 geometrically-diverse real-world objects and generalize to new objects with unseen shape or size.
PatchFormer: A neural architecture for self-supervised representation learning on images
In this paper, we propose a neural architecture for self-supervised representation learning on raw images called the PatchFormer which learns to model spatial dependencies across patches in a raw image.
Dynamical System Embedding for Efficient Intrinsically Motivated Artificial Agents
In this work, we develop a novel approach for the estimation of empowerment in unknown arbitrary dynamics from visual stimulus only, without sampling for the estimation of MIAS.
Data-Efficient Exploration with Self Play for Atari
To alleviate the reliance on reward engineering it is important to develop RL algorithms capable of efficiently acquiring skills with no rewards extrinsic to the agent.
Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning
Maximum Entropy Reinforcement Learning (MaxEnt RL) algorithms such as Soft Q-Learning (SQL) and Soft Actor-Critic trade off reward and policy entropy, which has the potential to improve training stability and robustness.
Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL
Meta-reinforcement learning (meta-RL) has proven to be a successful framework for leveraging experience from prior tasks to rapidly learn new related tasks, however, current meta-RL approaches struggle to learn in sparse reward environments.
Target Entropy Annealing for Discrete Soft Actor-Critic
Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings.
It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation
Training such agents efficiently requires automatic generation of a goal curriculum.
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning
In order to leverage unlabeled samples for reward learning, we infer pseudo-labels of the unlabeled samples based on the confidence of the preference predictor.
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
We also demonstrate that an effective style reward can be learned from a few seconds of motion capture data gathered from a German Shepherd and leads to energy-efficient locomotion strategies with natural gait transitions.
Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
The goal of imitation learning is to mimic expert behavior from demonstrations, without access to an explicit reward signal.
Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking
To continuously improve the quality of pseudo labels, we iterate the above steps by taking the trained student model as a new teacher and re-label real data using the refined teacher model.
Safe Exploration in Markov Decision Processes
We show that imposing safety by restricting attention to the resulting set of guaranteed safe policies is NP-hard.
On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning
From these findings, we advocate for evaluating future meta-RL methods on more challenging tasks and including multi-task pretraining with fine-tuning as a simple, yet strong baseline.
Masked World Models for Visual Control
Yet the current approaches typically train a single model end-to-end for learning both visual representations and dynamics, making it difficult to accurately model the interaction between robots and small objects.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
+1
Multi-Objective Policy Gradients with Topological Constraints
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety.
HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator
Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics.
Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
3D bounding boxes are a widespread intermediate representation in many computer vision applications.
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions
This paper proposes the Virtual MCTS (V-MCTS), a variant of MCTS that spends more search time on harder states and less search time on simpler states adaptively.
Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models
Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing impressive zero-shot and few-shot capabilities across a wide range of tasks.
StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCS
To further improve the performance of the stereo framework, StereoPose is equipped with a parallax attention module for stereo feature fusion and an epipolar loss for improving the stereo-view consistency of network predictions.
VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
We show that a text-conditioned diffusion model trained on pixel representations of images can be used to generate SVG-exportable vector graphics.
Multi-Environment Pretraining Enables Transfer to Action Limited Datasets
Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications.
Robust and Versatile Bipedal Jumping Control through Reinforcement Learning
This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world.
Aligning Text-to-Image Models using Human Feedback
Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.
Foundation Models for Decision Making: Problems, Methods, and Opportunities
In response to these developments, new paradigms are emerging for training foundation models to interact with other agents and perform long-term reasoning.
Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such can cause critical errors in high-performance applications.
Self-Supervised Instance Segmentation by Grasping
Leveraging this insight, we learn a grasp segmentation model to segment the grasped object from before and after grasp images.
Emergent Agentic Transformer from Chain of Hindsight Experience
Our method consists of relabelling target return of each trajectory to the maximum total reward among in sequence of trajectories and training an autoregressive model to predict actions conditioning on past states, actions, rewards, target returns, and task completion tokens, the resulting model, Agentic Transformer (AT), can learn to improve upon itself both at training and test time.
Probabilistic Adaptation of Text-to-Video Models
Large text-to-video models trained on internet-scale data have demonstrated exceptional capabilities in generating high-fidelity videos from arbitrary textual descriptions.
ALP: Action-Aware Embodied Learning for Perception
In addition, we show that by training on actively collected data more relevant to the environment and task, our method generalizes more robustly to downstream tasks compared to models pre-trained on fixed datasets such as ImageNet.
SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks
In this work, we present a focused study of the generalization capabilities of the pre-trained visual representations at the categorical level.
Learning to Model the World with Language
To interact with humans in the world, agents need to understand the diverse types of language that people use, relate them to the visual world, and act based on them.
Speed Co-Augmentation for Unsupervised Audio-Visual Pre-training
This work aims to improve unsupervised audio-visual pre-training.
Foundation Reinforcement Learning: towards Embodied Generalist Agents with Foundation Prior Assistance
Our method tolerates the unavoidable noise in embodied foundation models.
Learning Interactive Real-World Simulators
Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world.
Exploration with Principles for Diverse AI Supervision
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI.
Reinforcement Learning (RL)
Unsupervised Reinforcement Learning
Interactive Task Planning with Language Models
An interactive robot framework accomplishes long-horizon task planning and can easily generalize to new goals or distinct tasks, even during execution.
Video Language Planning
We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data.
Managing AI Risks in an Era of Rapid Progress
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards.
The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning
For tasks requiring object manipulation, we seamlessly and effectively exploit the complementarity of our senses of vision and touch.
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
Our benchmark results show that many models are vulnerable to the attack strategies in the Tensor Trust dataset.
Scalable Diffusion for Materials Generation
Lastly, we show that conditional generation with UniMat can scale to previously established crystal datasets with up to millions of crystals structures, outperforming random structure search (the current leading method for structure discovery) in discovering new stable materials.
Motion-Conditioned Image Animation for Video Editing
We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing.
Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average).
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning.
Any-point Trajectory Modeling for Policy Learning
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning.
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
This kind of data-driven optimization (DDO) presents a range of challenges beyond those in standard prediction problems, since we need models that successfully predict the performance of new designs that are better than the best designs seen in the training set.
Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control
Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing.
Video as the New Language for Real-World Decision Making
Moreover, we demonstrate how, like language models, video generation can serve as planners, agents, compute engines, and environment simulators through techniques such as in-context learning, planning and reinforcement learning.
MOKA: Open-Vocabulary Robotic Manipulation through Mark-Based Visual Prompting
In this paper, we present MOKA (Marking Open-vocabulary Keypoint Affordances), an approach that employs VLMs to solve robotic manipulation tasks specified by free-form language descriptions.
Twisting Lids Off with Two Hands
Manipulating objects with two multi-fingered hands has been a long-standing challenge in robotics, attributed to the contact-rich nature of many manipulation tasks and the complexity inherent in coordinating a high-dimensional bimanual system.
HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology.
Adversarial Attacks on Neural Network Policies
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification.
JUMBO: Scalable Multi-task Bayesian Optimization using Offline Data
Such a decomposition can dynamically control the reliability of information derived from the online and offline data and the use of pretrained neural networks permits scalability to large offline datasets.
Automatic Goal Generation for Reinforcement Learning Agents
Instead, we propose a method that allows an agent to automatically discover the range of tasks that it is capable of performing.
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
By parameterizing our learned model with a neural network, we are able to develop a scalable and efficient approach to exploration bonuses that can be applied to tasks with complex, high-dimensional state spaces.
Ranked #24 on
Atari Games
on Atari 2600 Q*Bert
Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects
Dense packing in pick-and-place systems is an important feature in many warehouse and logistics applications.
Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs
Deep learning methods for perception are the cornerstone of many robotic systems.
Gradient Estimation Using Stochastic Computation Graphs
In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external world.
AvE: Assistance via Empowerment
One difficulty in using artificial agents for human-assistive applications lies in the challenge of accurately assisting with a person's goal(s).
CLUTR: Curriculum Learning via Unsupervised Task Representation Learning
Recently, Unsupervised Environment Design (UED) emerged as a new paradigm for zero-shot generalization by simultaneously learning a task distribution and agent policies on the generated tasks.
Explaining Reinforcement Learning Policies through Counterfactual Trajectories
In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time.
Improving Long-Horizon Imitation Through Instruction Prediction
Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents.
Guiding Policies with Language via Meta-Learning
However, a single instruction may be insufficient to fully communicate our intent or, even if it is, may be insufficient for an autonomous agent to actually understand how to perform the desired task.
Variable Skipping for Autoregressive Range Density Estimation
In this paper, we explore a technique, variable skipping, for accelerating range density estimation over deep autoregressive models.
Emergence of Grounded Compositional Language in Multi-Agent Populations
By capturing statistical patterns in large corpora, machine learning has enabled significant advances in natural language processing, including in machine translation, question answering, and sentiment analysis.
Cooperative Inverse Reinforcement Learning
For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its environment in such a way that its actions contribute to the maximization of value for the humans.
Deep Spatial Autoencoders for Visuomotor Learning
Our method uses a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill with these feature points using an efficient reinforcement learning method based on local linear models.
Compositional Plan Vectors
We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training.
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
On a set of 26 benchmark Atari environments, MeanQ outperforms all tested baselines, including the best available baseline, SUNRISE, at 100K interaction steps in 16/26 environments, and by 68% on average.
Backprop KF: Learning Discriminative Deterministic State Estimators
We show that this procedure can be used to train state estimators that use complex input, such as raw camera images, which must be processed using expressive nonlinear function approximators such as convolutional neural networks.
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning
Our intuition is that disagreement in learned reward model reflects uncertainty in tailored human feedback and could be useful for exploration.
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
In this work, we propose multiplicative compositional policies (MCP), a method for learning reusable motor skills that can be composed to produce a range of complex behaviors.
Benchmarking Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL.
Hierarchical Few-Shot Imitation with Skill Transition Models
To this end, we present Few-shot Imitation with Skill Transition Models (FIST), an algorithm that extracts skills from offline data and utilizes them to generalize to unseen tasks given a few downstream demonstrations.
Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design
We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties with up to 10x more sample efficiency compared to a randomly initialized model.
Patch-based Object-centric Transformers for Efficient Video Generation
In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos.
Geometry-Aware Neural Rendering
Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics.
Hallucinative Topological Memory for Zero-Shot Visual Planning
In visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e. g., images obtained from self-supervised robot interaction.
Asynchronous Methods for Model-Based Reinforcement Learning
In this work, we propose an asynchronous framework for model-based reinforcement learning methods that brings down the run time of these algorithms to be just the data collection time.
Model-based Reinforcement Learning
reinforcement-learning
+1
It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation
We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals.
Adaptive Online Planning for Continual Lifelong Learning
We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change.
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation
Imitation learning is a powerful paradigm for robot skill acquisition.
Hierarchically Decoupled Imitation for Morphological Transfer
Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning.
Teachable Reinforcement Learning via Advice Distillation
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infrastructure and access to a human expert, and learning from intermediate forms of supervision (like binary preferences) is time-consuming and extracts little information from each human intervention.
Synkhronos: a Multi-GPU Theano Extension for Data Parallelism
We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism.
Deep Object-Centric Representations for Generalizable Robot Learning
We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy.
Task-Agnostic Morphology Evolution
Deep reinforcement learning primarily focuses on learning behavior, usually overlooking the fact that an agent's function is largely determined by form.
AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
To this end, we introduce AlberDICE, an offline MARL algorithm that alternatively performs centralized training of individual agents based on stationary distribution optimization.
Parallel Training of Deep Networks with Local Updates
Deep learning models trained on large data sets have been widely successful in both vision and language domains.
