Research map / Reinforcement learning / Offline RL
MOReL: Model-Based Offline Reinforcement Learning
Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, Thorsten Joachims
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 |
|---|---|---|---|
| MOReL (pessimistic MDP model-based) vs best model-free baseline | offline RL · Hopper-v2 Pure | return: 2774 -> 3642 | Improved |
| MOReL vs best baseline | offline RL · HalfCheetah-v2 (all datasets) | return: 6400 vs 5892 (Gauss-3) | Hurt |
| MOReL vs best baseline | offline RL · Walker2d-v2 | return: 2907 -> 3709 (Pure); 3490 vs 2899 (Eps-1) | Mixed |
| MOReL vs CQL | offline RL · D4RL average | normalized score: 54.85 -> 64.42 | Improved |
| add pessimistic MDP (USAD + HALT penalty) vs naive MBRL (ablation) | model-based NPG · MuJoCo Pure-partial | return stability | Improved |
| logging policy partially trained instead of random | MOReL · Hopper-v2 Pure | return: 2354 -> 3642 | Improved |
Later papers that compared with this method
17 later accepted papers report MOReL as a baseline in their results tables; 13 of them report a better number on most of the results they share with it.
- VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning (ICML 2026 · better on 1 of 1 shared result)
- Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation (ICLR 2026 · better on 1 of 1 shared result)
- Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning (TPAMI 2026 · better on 1 of 1 shared result)
- SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning (AAAI 2025 · better on 1 of 1 shared result)
- Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning (ICLR 2024 · better on 1 of 1 shared result)
- Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning (ICLR 2023 · better on 0 of 1 shared result)
- Efficient Offline Policy Optimization with a Learned Model (ICLR 2023 · better on 1 of 1 shared result)
- Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization (ICLR 2023 · better on 0 of 1 shared result)
9 more not listed.
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.
- MOPO — MOPO: Model-based Offline Policy Optimization (NeurIPS 2020) · better on 4 of 5 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
- MOPO: Model-based Offline Policy Optimization (NeurIPS 2020 · similarity 0.93)
- A Minimalist Approach to Offline Reinforcement Learning (NeurIPS 2021 · similarity 0.93)
- Leveraging Offline Data in Online Reinforcement Learning (ICML 2023 · similarity 0.92)
- A Clean Slate for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.92)
- Optimistic Model Rollouts for Pessimistic Offline Policy Optimization (AAAI 2024 · similarity 0.91)
- Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach (ICML 2025 · 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.
