Research map / Reinforcement learning / Visual and representation RL
Guided Meta-Policy Search
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 |
|---|---|---|---|
| Use supervised imitation of task experts for meta-optimization instead of an RL meta-objective | GMPS · Sawyer object pushing | sample efficiency vs. MAML: 4x improvement | Helped |
| Use supervised imitation of task experts for meta-optimization instead of an RL meta-objective | GMPS · Legged locomotion | sample efficiency vs. MAML: about 12x improvement | Helped |
| Use GMPS rather than PEARL | Meta-RL · In-distribution continuous-control tasks | performance | No clear effect |
| Use policy-gradient adaptation rather than contextual inference | Meta-RL · Out-of-distribution legged locomotion tasks | average return | Helped |
| Use demonstrations for imitation-based outer-loop meta-optimization | GMPS · Sparse-reward door opening and legged locomotion | task performance | Helped |
| Meta-learn adaptation instead of fine-tuning a multitask imitation policy | GMPS · Sparse-reward door opening and vision pusher | adaptation performance | Helped |
| Use imitation in the outer loop and RL in the inner loop for visual policies | GMPS · Vision-based tasks | reward | Helped |
Closest papers by meaning
- Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments (NeurIPS 2022 · similarity 0.93)
- Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator (NeurIPS 2024 · similarity 0.91)
- AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers (NeurIPS 2024 · similarity 0.91)
- DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Can Learned Optimization Make Reinforcement Learning Less Difficult? (NeurIPS 2024 · similarity 0.90)
- Meta-Reinforcement Learning via Exploratory Task Clustering (AAAI 2024 · similarity 0.90)
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.