Research map / Reinforcement learning / Offline RL
Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning
Shenghong He, Chao Yu, Qian Lin, Yile Liang, Donghui Li, Xuetao Ding
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| augment data with RT | BCQ · D4RL Maze2D-medium (sparse) | normalized return: 18.2 -> 55.3 | Improved |
| augment data with RT | BCQ · D4RL Antmaze-medium (diverse) | normalized return: 5.2 -> 56.4 | Improved |
| augment data with RT | IQL · D4RL Hopper medium-replay | normalized return: 96.8 -> 108.3 | Improved |
| augment data with RT | IQL · D4RL Maze2D-umaze (sparse) | normalized return: 20.1 -> 44.3 | Mixed |
| add reliability estimation to generation length (ablation) | RT · D4RL (IQL) | normalized return | Improved |
| generate backward instead of forward (ablation) | RT+BCQ · Maze2D and Antmaze | normalized return | Improved |
| use RT instead of ROMI/CABI/TATU/DStitch augmentation | scheduling policy · Industrial OFD data | TCR: 7 -> 10 | Improved |
| set reliability penalty beta to a moderate value (ablation) | RT+IQL · D4RL Hopper/Walker/Maze2D/Antmaze medium | normalized return | Mixed |
Closest papers by meaning
- Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling (ICLR 2025 · similarity 0.90)
- OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning (ICLR 2024 · similarity 0.90)
- The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Offline Safe Reinforcement Learning Using Trajectory Classification (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
