Research map / Reinforcement learning / Offline RL
Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief
Kaiyang Guo, yunfeng shao, Yanhui Geng
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 |
|---|---|---|---|
| increase k from 1 to 2 (ablation) | PMDB · hopper-medium (true MDP) | normalized score: 106.2 -> 106.8 | Improved |
| increase k from 2 to 3 (ablation) | PMDB · hopper-medium (true MDP) | normalized score: 106.8 -> 90.8 | Hurt |
| increase k from 1 to 3 (ablation) | PMDB · walker2d-medium (true MDP) | normalized score: 82.6 -> 105.1 | Improved |
| increase k from 1 to 3 (ablation) | PMDB · halfcheetah-medium (true MDP) | normalized score: 70.7 -> 77.3 | Improved |
| increase k from 1 to 3 (ablation) | PMDB · hopper-medium (AMG) | normalized score: 91.6 -> 106.6 | Improved |
| increase k from 1 to 3 (ablation) | PMDB · walker2d-medium (AMG) | normalized score: 33.3 -> 82.5 | Improved |
| increase k from 1 to 3 (ablation) | PMDB · halfcheetah-medium (AMG) | normalized score: 63.1 -> 70.1 | Improved |
| PMDB versus MOReL (model-based baseline) | PMDB · D4RL average | normalized score: 65.1 -> 88.2 | Improved |
| PMDB versus EDAC (model-free SoTA) | PMDB · D4RL average | normalized score: 85.2 -> 88.2 | Improved |
| PMDB versus EDAC on walker2d-medium-replay | PMDB · walker2d-medium-replay | normalized score: 87.1 -> 79.9 | Hurt |
| PMDB versus EDAC on halfcheetah-medium | PMDB · halfcheetah-medium | normalized score: 65.9 -> 75.6 | Improved |
| PMDB versus CQL on hopper-medium-replay | PMDB · hopper-medium-replay | normalized score: 86.3 -> 106.2 | Improved |
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.
- MOReL — MOReL: Model-Based Offline Reinforcement Learning (NeurIPS 2020) · better on 1 of 1 shared result
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
- Optimistic Model Rollouts for Pessimistic Offline Policy Optimization (AAAI 2024 · similarity 0.92)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.92)
- A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch (NeurIPS 2024 · similarity 0.91)
- Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning (ICLR 2024 · similarity 0.91)
- OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning (AAAI 2024 · similarity 0.91)
- The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
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.
