Search Results for author:
Found 3 papers, 0 papers with code
State-Constrained Offline Reinforcement Learning
Additionally, we introduce StaCQ, a deep learning algorithm that is both performance-driven on the D4RL benchmark datasets and closely aligned with our theoretical propositions.
Model-based trajectory stitching for improved behavioural cloning and its applications
Furthermore, using the D4RL benchmarking suite, we demonstrate that state-of-the-art results are obtained by combining TS with two existing offline learning methodologies reliant on BC, model-based offline planning (MBOP) and policy constraint (TD3+BC).
Model-based Trajectory Stitching for Improved Offline Reinforcement Learning
We propose a model-based data augmentation strategy, Trajectory Stitching (TS), to improve the quality of sub-optimal historical trajectories.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
