Search Results for author:
Found 43 papers, 5 papers with code
Imitating Language via Scalable Inverse Reinforcement Learning
We focus on investigating the inverse reinforcement learning (IRL) perspective to imitation, extracting rewards and directly optimizing sequences instead of individual token likelihoods and evaluate its benefits for fine-tuning large language models.
Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision.
Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution
Recent reinforcement learning approaches have shown surprisingly strong capabilities of bang-bang policies for solving continuous control benchmarks.
Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning
Recent advances in real-world applications of reinforcement learning (RL) have relied on the ability to accurately simulate systems at scale.
Foundations for Transfer in Reinforcement Learning: A Taxonomy of Knowledge Modalities
Contemporary artificial intelligence systems exhibit rapidly growing abilities accompanied by the growth of required resources, expansive datasets and corresponding investments into computing infrastructure.
Replay across Experiments: A Natural Extension of Off-Policy RL
Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL).
Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning
We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment.
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World
For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and benchmark algorithms.
Towards A Unified Agent with Foundation Models
Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others.
Massively Scalable Inverse Reinforcement Learning in Google Maps
Inverse reinforcement learning (IRL) offers a powerful and general framework for learning humans' latent preferences in route recommendation, yet no approach has successfully addressed planetary-scale problems with hundreds of millions of states and demonstration trajectories.
Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be composed into complex behavioral strategies in dynamic environments.
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents.
Solving Continuous Control via Q-learning
While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces.
MO2: Model-Based Offline Options
The ability to discover useful behaviours from past experience and transfer them to new tasks is considered a core component of natural embodied intelligence.
Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data
We propose the Offline Distillation Pipeline to break this trade-off by separating the training procedure into an online interaction phase and an offline distillation phase. Second, we find that training with the imbalanced off-policy data from multiple environments across the lifetime creates a significant performance drop.
Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots.
The Challenges of Exploration for Offline Reinforcement Learning
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour.
Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies
We demonstrate in manipulation domains that the method can effectively cluster offline data into distinct, executable behaviours, while retaining the flexibility of a continuous latent variable model.
Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation
In this work, we extend hindsight relabelling mechanisms to guide exploration along task-specific distributions implied by a small set of successful demonstrations.
Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies
Reinforcement learning (RL) for continuous control typically employs distributions whose support covers the entire action space.
Is Curiosity All You Need? On the Utility of Emergent Behaviours from Curious Exploration
Curiosity-based reward schemes can present powerful exploration mechanisms which facilitate the discovery of solutions for complex, sparse or long-horizon tasks.
From Motor Control to Team Play in Simulated Humanoid Football
In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds.
Representation Matters: Improving Perception and Exploration for Robotics
Furthermore, the value of each representation is evaluated in terms of three properties: dimensionality, observability and disentanglement.
Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs.
Data-efficient Hindsight Off-policy Option Learning
We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm.
Simple Sensor Intentions for Exploration
In particular, we show that a real robotic arm can learn to grasp and lift and solve a Ball-in-a-Cup task from scratch, when only raw sensor streams are used for both controller input and in the auxiliary reward definition.
Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
In contrast, we propose to treat hybrid problems in their 'native' form by solving them with hybrid reinforcement learning, which optimizes for discrete and continuous actions simultaneously.
Disentangled Cumulants Help Successor Representations Transfer to New Tasks
This is in contrast to the state-of-the-art reinforcement learning agents, which typically start learning each new task from scratch and struggle with knowledge transfer.
Attention-Privileged Reinforcement Learning
Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space).
Attention Privileged Reinforcement Learning for Domain Transfer
Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments.
Compositional Transfer in Hierarchical Reinforcement Learning
The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements.
General Reinforcement Learning
Hierarchical Reinforcement Learning
+4
Guiding Physical Intuition with Neural Stethoscopes
Using an adversarial stethoscope, the network is successfully de-biased, leading to a performance increase from 66% to 88%.
Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
Recent successes in machine learning have led to a shift in the design of autonomous systems, improving performance on existing tasks and rendering new applications possible.
On Machine Learning and Structure for Mobile Robots
Due to recent advances - compute, data, models - the role of learning in autonomous systems has expanded significantly, rendering new applications possible for the first time.
Scrutinizing and De-Biasing Intuitive Physics with Neural Stethoscopes
Conversely, training on an easy dataset where visual cues are positively correlated with stability, the baseline model learns a bias leading to poor performance on a harder dataset.
TACO: Learning Task Decomposition via Temporal Alignment for Control
Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks.
Incremental Adversarial Domain Adaptation for Continually Changing Environments
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models.
Generative Adversarial Network
Unsupervised Domain Adaptation
Mutual Alignment Transfer Learning
Training robots for operation in the real world is a complex, time consuming and potentially expensive task.
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.
Addressing Appearance Change in Outdoor Robotics with Adversarial Domain Adaptation
Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics.
Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
Recent advances have shown the capability of Fully Convolutional Neural Networks (FCN) to model cost functions for motion planning in the context of learning driving preferences purely based on demonstration data from human drivers.
Watch This: Scalable Cost-Function Learning for Path Planning in Urban Environments
In this work, we present an approach to learn cost maps for driving in complex urban environments from a very large number of demonstrations of driving behaviour by human experts.
Maximum Entropy Deep Inverse Reinforcement Learning
This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem.
