Related papers: Zero-Shot Whole-Body Humanoid Control via Behavior…
Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…
Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…
We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining…
Learning agile humanoid behaviors from human motion offers a powerful route to natural, coordinated control, but existing approaches face a persistent trade-off: reference-tracking policies are often brittle outside the demonstration…
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…
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,…
A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centric RL paradigm…
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…
Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…
This paper addresses the challenge of terrain-adaptive dynamic locomotion in humanoid robots, a problem traditionally tackled by optimization-based methods or reinforcement learning (RL). Optimization-based methods, such as model-predictive…
Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are only able to produce near-optimal policies for the reward functions that are in the span of some…
Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…
Humanoid robots have the potential to mimic human motions with high visual fidelity, yet translating these motions into practical, physical execution remains a significant challenge. Existing techniques in the graphics community often…
Collecting and automatically obtaining reward signals from real robotic visual data for the purposes of training reinforcement learning algorithms can be quite challenging and time-consuming. Methods for utilizing unlabeled data can have a…
Synthesizing complex whole-body manipulation behaviors has fundamental challenges due to the rapidly growing combinatorics inherent to contact interaction planning. While model-based methods have shown promising results in solving…
Offline reinforcement learning (RL) enables learning control policies by utilizing only prior experience, without any online interaction. This can allow robots to acquire generalizable skills from large and diverse datasets, without any…
Zero-shot reinforcement learning (RL) promises to provide agents that can perform any task in an environment after an offline, reward-free pre-training phase. Methods leveraging successor measures and successor features have shown strong…
Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous…
Deep reinforcement learning (RL) algorithms can learn complex robotic skills from raw sensory inputs, but have yet to achieve the kind of broad generalization and applicability demonstrated by deep learning methods in supervised domains. We…
Reinforcement learning (RL) has demonstrated impressive performance in legged locomotion over various challenging environments. However, due to the sim-to-real gap and lack of explainability, unconstrained RL policies deployed in the real…