Related papers: Generalizing from References using a Multi-Task Re…
Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…
We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…
Reinforcement learning (RL) is effective in many robotic applications, but it requires extensive exploration of the state-action space, during which behaviors can be unsafe. This significantly limits its applicability to large robots with…
Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for…
Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots.…
Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…
Humanoid locomotion is a challenging task due to its inherent complexity and high-dimensional dynamics, as well as the need to adapt to diverse and unpredictable environments. In this work, we introduce a novel learning framework for…
Deep reinforcement learning (RL) based controllers for legged robots have demonstrated impressive robustness for walking in different environments for several robot platforms. To enable the application of RL policies for humanoid robots in…
Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands. Scripting policies from scratch is intractable due to the high-dimensional control space, and training policies…
Humanoid robots that autonomously interact with physical environments over extended horizons represent a central goal of embodied intelligence. Existing approaches rely on reference motions or task-specific rewards, tightly coupling…
Generative adversarial imitation learning (GAIL) has attracted increasing attention in the field of robot learning. It enables robots to learn a policy to achieve a task demonstrated by an expert while simultaneously estimating the reward…
Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute…
Complex, multi-task problems have proven to be difficult to solve efficiently in a sparse-reward reinforcement learning setting. In order to be sample efficient, multi-task learning requires reuse and sharing of low-level policies. To…
Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…
Reinforcement learning has shown great promise for synthesizing realistic human behaviors by learning humanoid control policies from motion capture data. However, it is still very challenging to reproduce sophisticated human skills like…
Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of…
Although deep RL models have shown a great potential for solving various types of tasks with minimal supervision, several key challenges remain in terms of learning from limited experience, adapting to environmental changes, and…
Humans can flexibly generalize knowledge across domains by leveraging structured relational representations. While prior research has shown how such representations support analogical reasoning, less is known about how they are recruited to…
Recent advances in language modeling and vision stem from training large models on diverse, multi-task data. This paradigm has had limited impact in value-based reinforcement learning (RL), where improvements are often driven by small…
Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where…