Research map / Reinforcement learning / Policy gradient and actor-critic
When to Trust Your Model: Model-Based Policy Optimization
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 short model rollouts (model-generated data) to SAC at high update ratio (ablation) | SAC · MuJoCo Hopper | sample efficiency | Helped |
| fix rollout length at k=1 instead of linearly increasing 1 to 15 (ablation) | MBPO · MuJoCo Hopper | return | No clear effect |
| use long 200-step model rollouts (ablation) | MBPO · MuJoCo Hopper | return | Hurt |
| use 500-step model rollouts (ablation) | MBPO · MuJoCo Hopper | return | Hurt |
| add model-based value expansion targets (ablation) | MBPO · MuJoCo | return | No clear effect |
| add H-step value expansion | SAC · MuJoCo Hopper | return | Helped |
| MBPO vs SAC | SAC · MuJoCo Ant | sample efficiency | Helped |
Closest papers by meaning
- On-Policy Model Errors in Reinforcement Learning (ICLR 2022 · similarity 0.92)
- MOPO: Model-based Offline Policy Optimization (NeurIPS 2020 · similarity 0.91)
- Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025 · similarity 0.91)
- The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Optimistic Model Rollouts for Pessimistic Offline Policy Optimization (AAAI 2024 · similarity 0.89)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
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.