Research map / Reinforcement learning / Offline RL
Model-Based Offline Weighted Policy Optimization (Student Abstract)
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL random halfcheetah | normalized score: 35.4 ± 2.5 -> 33.5 ± 2.6 | Hurt |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL random hopper | normalized score: 11.7 ± 0.4 -> 11.7 ± 0.8 | No clear effect |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL random walker2d | normalized score: 13.6 ± 2.6 -> 15.8 ± 4.8 | Helped |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium halfcheetah | normalized score: 42.3 ± 1.6 -> 47.1 ± 0.7 | Helped |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium hopper | normalized score: 28.0 ± 12.4 -> 23.7 ± 4.0 | Hurt |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium walker2d | normalized score: 17.8 ± 19.3 -> 74.8 ± 5.9 | Helped |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium-replay halfcheetah | normalized score: 53.1 ± 2.0 -> 57.6 ± 1.2 | Helped |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium-replay hopper | normalized score: 67.5 ± 24.7 -> 69.0 ± 13.6 | Helped |
| Add weighted Bellman updates using model-confidence and behavioral-prior weights to MOPO | MOPO · D4RL medium-replay walker2d | normalized score: 39.0 ± 9.6 -> 46.3 ± 17.9 | Helped |
| Vary λ to balance model-confidence weighting and behavioral-prior weighting (ablation) | MOWPO · D4RL random and medium datasets | normalized score | Mixed |
| Vary λ to balance model-confidence weighting and behavioral-prior weighting (ablation) | MOWPO · D4RL medium-replay datasets | normalized score | Mixed |
Closest papers by meaning
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.91)
- SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning (AAAI 2025 · similarity 0.91)
- Optimistic Model Rollouts for Pessimistic Offline Policy Optimization (AAAI 2024 · similarity 0.90)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- OCEAN-MBRL: Offline Conservative Exploration for Model-Based Offline Reinforcement Learning (AAAI 2024 · similarity 0.90)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · 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.