4 papers
CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation
Wentian Wang, Chutong Wen, Hongxu Ma +6
We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA replaces raw simulator-parame…
Success in Humanoid Reinforcement Learning under Partial Observation
Wuhao Wang, Zhiyong Chen
Reinforcement learning has been widely applied to robotic control, but effective policy learning under partial observability remains a major challenge, especially in high-dimension…
A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability
Wuhao Wang, Zhiyong Chen
Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMD…
Multi-State TD Target for Model-Free Reinforcement Learning
Wuhao Wang, Zhiyong Chen, Lepeng Zhang
Temporal difference (TD) learning is a fundamental technique in reinforcement learning that updates value estimates for states or state-action pairs using a TD target. This target…