Research map / Reinforcement learning / Visual and representation RL
The Importance of Sampling inMeta-Reinforcement Learning
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 explore term (differentiate through initial sampling distribution) to MAML, giving E-MAML | MAML · Krazy World | sample efficiency / learning speed | Helped |
| zero reward contribution of Explore-rollouts in backward pass, giving E-RL2 | RL2 · Krazy World | final reward | Helped |
| E-RL2 variant of RL2 on mazes | RL2 · Mazes 20x20 | reward | Helped |
| add explore term to MAML | MAML · Krazy World | fraction of tile types visited | Helped |
Closest papers by meaning
- MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning (ICLR 2024 · similarity 0.90)
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (AAAI 2024 · similarity 0.88)
- Meta-World+: An Improved, Standardized, RL Benchmark (NeurIPS 2025 · similarity 0.88)
- DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Meta-Reinforcement Learning via Exploratory Task Clustering (AAAI 2024 · similarity 0.87)
- Can Learned Optimization Make Reinforcement Learning Less Difficult? (NeurIPS 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.