Research map / Reinforcement learning / Offline RL
Offline Model-based Adaptable Policy Learning
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 |
|---|---|---|---|
| MAPLE adaptable policy instead of MOPO | MOPO · Walker2d-medium | normalized score: 11.8 -> 56.3 | Helped |
| MAPLE instead of MOPO | MOPO · Walker2d-mixed | normalized score: 39.0 -> 76.7 | Helped |
| MAPLE instead of MOPO | MOPO · Hopper-medium | normalized score: 28.0 -> 21.1 | Hurt |
| MAPLE instead of MOPO | MOPO · Hopper-med-expert | normalized score: 23.7 -> 42.5 | Helped |
| MAPLE instead of MOPO-loose (same hyperparameters) (ablation) | MOPO-loose · HalfCheetah-mixed | normalized score: 36.9 -> 59.0 | Helped |
| MAPLE instead of MOPO-loose (ablation) | MOPO-loose · Walker2d-medium | normalized score: 32.6 -> 56.3 | Helped |
| MAPLE instead of model-free CQL | CQL · Hopper-med-expert | normalized score: 98.7 -> 42.5 | Hurt |
| enlarge ensemble from 14 models to 200 (MAPLE-200) | MAPLE · Walker2d-medium | normalized score: 56.3 -> 81.3 | Helped |
| MAPLE-200 instead of MAPLE | MAPLE · Hopper-med-expert | normalized score: 42.5 -> 95.3 | Helped |
| MAPLE-200 instead of MAPLE | MAPLE · Walker2d-med-expert | normalized score: 73.8 -> 107.0 | Helped |
| MAPLE-200 instead of MAPLE | MAPLE · HalfCheetah-med-expert | normalized score: 63.5 -> 55.4 | Hurt |
| MAPLE-200 instead of MAPLE | MAPLE · Hopper-mixed | normalized score: 87.5 -> 85.0 | No clear effect |
Closest papers by meaning
- Adaptive Policy Learning for Offline-to-Online Reinforcement Learning (AAAI 2023 · similarity 0.91)
- A Unified Framework for Alternating Offline Model Training and Policy Learning (NeurIPS 2022 · similarity 0.91)
- MOPO: Model-based Offline Policy Optimization (NeurIPS 2020 · similarity 0.91)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Localized Dynamics-Aware Domain Adaption for Off-Dynamics Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 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.