4 accepted papers
For full-size humanoid robots, reliable locomotion on complex terrains—such as long staircases—remains challenging, even with recent advances in reinforcement-learning-based control. In such settings, limited perception, ambiguous terrain cues, and insufficient adaptation of gait timing can cause ev
Achieving efficient and robust whole-body control (WBC) is essential for enabling humanoid robots to perform complex tasks in dynamic environments. Despite the success of reinforcement learning (RL) in this domain, its sample inefficiency remains a significant challenge due to the intricate dynamics
Offline-to-online reinforcement learning (RL) provides a promising solution to improving suboptimal offline pre-trained policies through online fine-tuning. However, one efficient method, unconstrained fine-tuning, often suffers from severe policy collapse due to excessive distribution shift. To ens…
Recent approaches have utilized self-supervised auxiliary tasks as representation learning to improve the performance and sample efficiency of vision-based reinforcement learning algorithms in single-agent settings. However, in multi-agent reinforcement learning (MARL), these techniques face challen…