Research map / Reinforcement learning / Offline RL
Offline Reinforcement Learning with Value-based Episodic Memory
Xiaoteng Ma, Yiqin Yang, Hao Hu, Jun Yang, Chongjie Zhang, Qianchuan Zhao, Bin Liang, Qihan Liu
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 |
|---|---|---|---|
| Use VEM rather than the strongest reported baseline | Offline RL · AntMaze tasks | normalized score | Improved |
| Use VEM rather than the strongest reported baseline | Offline RL · Adroit tasks | normalized score | Mixed |
| Use VEM rather than the strongest reported baseline | Offline RL · MuJoCo tasks | normalized score | Mixed |
| Replace EVL with BCQ value learning (ablation) | VEM · Adroit-human tasks | normalized score | Hurt |
| Replace episodic memory planning with standard n-step value estimation (ablation) | VEM · AntMaze tasks | convergence speed | Hurt |
| Replace expectile loss with quantile loss (ablation) | VEM · Adroit tasks | stability | Hurt |
| Increase expectile fraction too far (for example, tau=0.9) (ablation) | VEM · Adroit pen-human | performance | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BAIL — BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning (NeurIPS 2020) · better on 6 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning (ICLR 2025 · similarity 0.91)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Is Value Learning Really the Main Bottleneck in Offline RL? (NeurIPS 2024 · similarity 0.91)
- Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement Learning (ICML 2024 · similarity 0.91)
- A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning (AAAI 2024 · similarity 0.90)
- Reasoning with Latent Diffusion in Offline Reinforcement Learning (ICLR 2024 · similarity 0.90)
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.
