Search Results for author:
Found 39 papers, 18 papers with code
Decision Transformer under Random Frame Dropping
Typical RL methods usually require considerable online interaction data that are costly and unsafe to collect in the real world.
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
To test this hypothesis, we devise two practical robust training mechanisms through computing the adversarial noise and regularizing the value network's spectral norm to directly regularize the Lipschitz condition of the value functions.
Scene Synthesis from Human Motion
Large-scale capture of human motion with diverse, complex scenes, while immensely useful, is often considered prohibitively costly.
Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner.
On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet.
See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation
Humans use all of their senses to accomplish different tasks in everyday activities.
E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance
Specifically, we introduce Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance(E-MAPP), a novel framework that leverages parallel programs to guide multiple agents to efficiently accomplish goals that require planning over $10+$ stages.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
To alleviate this issue, we propose to differentiate through the Bellman fixed-point equation to decouple forward and backward passes for Value Iteration Network and its variants, which enables constant backward cost (in planning horizon) and flexible forward budget and helps scale up to large tasks.
Simple Emergent Action Representations from Multi-Task Policy Training
The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks.
Extraneousness-Aware Imitation Learning
To tackle this problem, we introduce Extraneousness-Aware Imitation Learning (EIL), a self-supervised approach that learns visuomotor policies from third-person demonstrations with extraneous subsequences.
USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation
Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance?
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods.
RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks
Our learned model-based planning framework is comparable to and sometimes better than human subjects on the tested tasks.
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments.
NovelD: A Simple yet Effective Exploration Criterion
We analyze NovelD thoroughly in MiniGrid and found that empirically it helps the agent explore the environment more uniformly with a focus on exploring beyond the boundary.
Multi-Person 3D Motion Prediction with Multi-Range Transformers
Thus, instead of predicting each human pose trajectory in isolation, we introduce a Multi-Range Transformers model which contains of a local-range encoder for individual motion and a global-range encoder for social interactions.
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets.
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Our key insight is that proprioceptive states only offer contact measurements for immediate reaction, whereas an agent equipped with visual sensory observations can learn to proactively maneuver environments with obstacles and uneven terrain by anticipating changes in the environment many steps ahead.
DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation
We address the problem of safely solving complex bimanual robot manipulation tasks with sparse rewards.
Towards Learning to Play Piano with Dexterous Hands and Touch
The virtuoso plays the piano with passion, poetry and extraordinary technical ability.
PyTouch: A Machine Learning Library for Touch Processing
With the increased availability of rich tactile sensors, there is an equally proportional need for open-source and integrated software capable of efficiently and effectively processing raw touch measurements into high-level signals that can be used for control and decision-making.
Solving Compositional Reinforcement Learning Problems via Task Reduction
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems.
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization
We propose a simple, general and effective technique, Reward Randomization for discovering diverse strategic policies in complex multi-agent games.
BeBold: Exploration Beyond the Boundary of Explored Regions
In this paper, we analyze the pros and cons of each method and propose the regulated difference of inverse visitation counts as a simple but effective criterion for IR.
Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
Synthesizing 3D human motion plays an important role in many graphics applications as well as understanding human activity.
Multi-Agent Collaboration via Reward Attribution Decomposition
In this work, we propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge and supports ad hoc team play.
Hierarchical Style-based Networks for Motion Synthesis
Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world.
Video Prediction via Example Guidance
In video prediction tasks, one major challenge is to capture the multi-modal nature of future contents and dynamics.
Multi-Task Reinforcement Learning with Soft Modularization
While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other.
Ranked #1 on
Meta-Learning
on MT50
Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation
The agent is first presented with previous experiences in the training environment, along with task description in the form of trajectory-level sparse rewards.
Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization
In this paper, we propose Scoring-Aggregating-Planning (SAP), a framework that can learn task-agnostic semantics and dynamics priors from arbitrary quality interactions as well as the corresponding sparse rewards and then plan on unseen tasks in zero-shot condition.
Composable Semi-parametric Modelling for Long-range Motion Generation
Learning diverse and natural behaviors is one of the longstanding goal for creating intelligent characters in the animated world.
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling
Imitation learning, followed by reinforcement learning algorithms, is a promising paradigm to solve complex control tasks sample-efficiently.
Disentangling Propagation and Generation for Video Prediction
A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated.
Modular Architecture for StarCraft II with Deep Reinforcement Learning
We present a novel modular architecture for StarCraft II AI.
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL.
Reinforcement Learning from Imperfect Demonstrations
We propose a unified reinforcement learning algorithm, Normalized Actor-Critic (NAC), that effectively normalizes the Q-function, reducing the Q-values of actions unseen in the demonstration data.
End-to-end Learning of Driving Models from Large-scale Video Datasets
Robust perception-action models should be learned from training data with diverse visual appearances and realistic behaviors, yet current approaches to deep visuomotor policy learning have been generally limited to in-situ models learned from a single vehicle or a simulation environment.
Natural Language Object Retrieval
In this paper, we address the task of natural language object retrieval, to localize a target object within a given image based on a natural language query of the object.
Ranked #11 on
Referring Expression Comprehension
on Talk2Car
