Related papers: Generalizing from References using a Multi-Task Re…

We present a unified framework for multi-task locomotion and manipulation policy learning grounded in a contact-explicit representation. Instead of designing different policies for different tasks, our approach unifies the definition of a…

Humanoid robots have the promise of locomoting like humans, including fast and dynamic running. Recently, reinforcement learning (RL) controllers that can mimic human motions have become popular as they can generate very dynamic behaviors,…

We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These inductive tasks have similar overarching goals but they differ…

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…

Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new…

In order for autonomous mobile robots to navigate in human spaces, they must abide by our social norms. Reinforcement learning (RL) has emerged as an effective method to train sequential decision-making policies that are able to respect…

We present a deep learning method for composite and task-driven motion control for physically simulated characters. In contrast to existing data-driven approaches using reinforcement learning that imitate full-body motions, we learn…

Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard perception. Directly applying reinforcement learning (RL) with…

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, but the…

Humanoid motion tracking policies are central to building teleoperation pipelines and hierarchical controllers, yet they face a fundamental challenge: the embodiment gap between humans and humanoid robots. Current approaches address this…

Humanoid robots have demonstrated robust locomotion capabilities using Reinforcement Learning (RL)-based approaches. Further, to obtain human-like behaviors, existing methods integrate human motion-tracking or motion prior in the RL…

We present a method for training reference-guided, perceptive reinforcement learning locomotion policies for humanoid robots in which reference trajectories are modulated in training to be consistent with terrain geometry. Aiming to deploy…

Reinforcement learning (RL)-based motion imitation methods trained on demonstration data can effectively learn natural and expressive motions with minimal reward engineering but often struggle to generalize to novel environments. We address…

We present a reinforcement learning framework for autonomous goalkeeping with humanoid robots in real-world scenarios. While prior work has demonstrated similar capabilities on quadrupedal platforms, humanoid goalkeeping introduces two…

As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and…

Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce…

Model-based reinforcement learning (RL) has shown great potential in various control tasks in terms of both sample-efficiency and final performance. However, learning a generalizable dynamics model robust to changes in dynamics remains a…

Reinforcement learning (RL) is a framework to optimize a control policy using rewards that are revealed by the system as a response to a control action. In its standard form, RL involves a single agent that uses its policy to accomplish a…

Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where…

Unsupervised reinforcement learning (RL) aims at pre-training agents that can solve a wide range of downstream tasks in complex environments. Despite recent advancements, existing approaches suffer from several limitations: they may require…