Research map / Reinforcement learning / Visual and representation RL
META LEARNING SHARED HIERARCHIES
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 shared learned sub-policies and fine-tune a task-specific master policy | MLSH · Walk/Crawl combination task | reward: 6055 -> 14333 | Helped |
| Use transferred sub-policies and fine-tune the master policy | MLSH · Ant Obstacle task | reward: 0 -> 193 | Helped |
| Remove the warmup period before updating sub-policies (ablation) | MLSH on 2D Moving Bandits · 2D Moving Bandits | reward | Hurt |
| Run the master policy on the same timescale as the sub-policies (ablation) | MLSH on 2D Moving Bandits · 2D Moving Bandits | reward | Hurt |
Closest papers by meaning
- Skill-based Meta-Reinforcement Learning (ICLR 2022 · similarity 0.89)
- Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments (NeurIPS 2022 · similarity 0.89)
- Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies (ICLR 2019 · similarity 0.89)
- Hierarchical Skills for Efficient Exploration (NeurIPS 2021 · similarity 0.88)
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024 · similarity 0.86)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.86)
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.