Research map / Reinforcement learning / Policy gradient and actor-critic
Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative 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 estimated-uncertainty penalty to model-based policy optimization (POMBU versus MEPPO) | HalfCheetah · HalfCheetah (H=200) | return: $449\pm226$ -> $852\pm21$ | Helped |
| Use conservative uncertainty-aware policy optimization with α=0.5 (ablation) | POMBU · Cheetah (H=200, 200K samples) | final return | Helped |
| Use conservative uncertainty-aware policy optimization with α=0.75 (ablation) | POMBU · Cheetah (H=200, 200K samples) | final return | Helped |
| Increase α substantially (ablation) | POMBU · Cheetah (early training) | return | Hurt |
| Add uncertainty-aware exploration using β=10 rather than β=0 (ablation) | POMBU · Cheetah | return | Helped |
| Add an uncertainty penalty to policy optimization (α>0 versus α=0) (ablation) | POMBU · HalfCheetah (H=200, early training) | model overfitting | Helped |
| Estimate model-based uncertainty and optimize policies conservatively | POMBU · Mujoco continuous-control tasks | sample efficiency | Helped |
| Use POMBU rather than SAC | HalfCheetah · HalfCheetah (H=200) | return: $615\pm64$ -> $852\pm21$ | Helped |
Closest papers by meaning
- Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees (ICLR 2019 · similarity 0.90)
- Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models (NeurIPS 2018 · similarity 0.89)
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.89)
- COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL (ICLR 2024 · similarity 0.88)
- Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- SOMBRL: Scalable and Optimistic Model-Based RL (NeurIPS 2025 · similarity 0.87)
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.