Organizing samples in a trajective manner can improve the learning efficiency for offline RL algorithms.
May 1, 2024
An experience resampling method that uses gradient-direction uncertainty for more stable policy improvement.
Jan 1, 2024
A unified platform and benchmark suite for reinforcement learning with diverse human feedback.
Jan 1, 2024
A unified keyframe identification and skill annotation method for long-horizon robot demonstrations.
Jan 1, 2024
An offline-to-online reinforcement learning method that improves transition efficiency with Q-ensembles.
Jan 1, 2024
An unsupervised reinforcement learning method that improves efficiency with a multi-choice dynamics model.
Jan 1, 2023
A deep reinforcement learning approach for generating failure-inducing inputs in cyber-physical systems testing.
Jan 1, 2021