9 papers
VIGOR: Visual Goal-In-Context Inference for Unified Humanoid Fall Safety
Osher Azulay, Zhengjie Xu, Andrew Scheffer +1
Reliable fall recovery is critical for humanoids operating in cluttered environments. Unlike quadrupeds or wheeled robots, humanoids experience high-energy impacts, complex whole-b…
PRISM: Parallel Reward Integration with Symmetry for MORL
Finn van der Knaap, Kejiang Qian, Zheng Xu +1
This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal frequency. Such heterogeneity allows dense objectives…
StepScorer: Accelerating Reinforcement Learning with Step-wise Scoring and Psychological Regret Modeling
Zhe Xu
Reinforcement learning algorithms often suffer from slow convergence due to sparse reward signals, particularly in complex environments where feedback is delayed or infrequent. Thi…
Inferring Causal Graph Temporal Logic Formulas to Expedite Reinforcement Learning in Temporally Extended Tasks
Hadi Partovi Aria, Zhe Xu
Decision-making tasks often unfold on graphs with spatial-temporal dynamics. Black-box reinforcement learning often overlooks how local changes spread through network structure, li…
Unified Humanoid Fall-Safety Policy from a Few Demonstrations
Zhengjie Xu, Ye Li, Kwan-yee Lin +1
Falling is an inherent risk of humanoid mobility. Maintaining stability is thus a primary safety focus in robot control and learning, yet no existing approach fully averts loss of…
Expediting Reinforcement Learning by Incorporating Knowledge About Temporal Causality in the Environment
Jan Corazza, Hadi Partovi Aria, Daniel Neider +1
Reinforcement learning (RL) algorithms struggle with learning optimal policies for tasks where reward feedback is sparse and depends on a complex sequence of events in the environm…