Search Results for author:
Found 4 papers, 2 papers with code
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning
In the online setting, ADMPO-ON demonstrates improved sample efficiency compared to previous state-of-the-art methods.
Episodic Return Decomposition by Difference of Implicitly Assigned Sub-Trajectory Reward
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed case where the only feedback is the episodic reward obtained at the end of an episode.
Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments
In this work, we focus on imitator learning based on only one expert demonstration.
Model-Bellman Inconsistency for Model-based Offline Reinforcement Learning
MOBILE conducts uncertainty quantification through the inconsistency of Bellman estimations under an ensemble of learned dynamics models, which can be a better approximator to the true Bellman error, and penalizes the Bellman estimation based on this uncertainty.
