Research map / Reinforcement learning / Policy gradient and actor-critic
Adaptation Augmented Model-based Policy Optimization
Jian Shen, Hang Lai, Minghuan Liu, Han Zhao, Yong Yu, Weinan Zhang
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 |
|---|---|---|---|
| add feature-based model adaptation (FAMPO) to MBPO (ablation) | MBPO · Hopper, Walker2d, Ant (few interactions) | average return | Improved |
| add instance-based model adaptation (IAMPO) to MBPO (ablation) | MBPO · Hopper, Walker2d, Ant (few interactions) | average return | Improved |
| add uncertainty-weighted sampling to model adaptation (ablation) | FAMPO and IAMPO · Hopper and Walker2d | average return | Improved |
| add uncertainty-weighted sampling to model adaptation (ablation) | FAMPO and IAMPO · Ant | average return | No clear effect |
| add model adaptation to MBPO | MBPO · six MuJoCo tasks | sample efficiency and return | Improved |
| add feature alignment loss (FAMPO) to MBPO | MBPO · Hopper | Wasserstein-1 distance of real vs simulated features | Improved |
| add model adaptation to MBPO | MBPO · compounding error vs trajectory length h | compounding error | Improved |
| increase adaptation iterations G2 too far (ablation) | FAMPO · Hopper (epoch 40) | average return | Mixed |
| increase sampling temperature sigma too far (ablation) | IAMPO · Walker2d (epoch 100) | average return | Hurt |
Closest papers by meaning
- Model-based Policy Optimization with Unsupervised Model Adaptation (NeurIPS 2020 · similarity 0.94)
- Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy (ICML 2023 · similarity 0.89)
- Provably Efficient Model-based Policy Adaptation (ICML 2020 · similarity 0.89)
- Bidirectional Model-based Policy Optimization (ICML 2020 · similarity 0.89)
- Gradient-Aware Model-Based Policy Search (AAAI 2020 · similarity 0.89)
- Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control (ICLR 2024 · 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.
