3 papers
cs.RO2025
Real-World Reinforcement Learning of Active Perception Behaviors
Edward S. Hu, Jie Wang, Xingfang Yuan +5
A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly…
cs.LG2025
A Theoretical Justification for Asymmetric Actor-Critic Algorithms
Gaspard Lambrechts, Damien Ernst, Aditya Mahajan
In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages add…
cs.LG2024
Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures
Adrien Bolland, Gaspard Lambrechts, Damien Ernst
Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In th…