Research map / Reinforcement learning / Visual and representation RL
Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
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 a meta-learned adaptation policy instead of a random adaptation policy (ablation) | MSGI · Playground | normalized reward | Helped |
| Use explicit subtask graph inference and graph-conditioned execution instead of implicit meta-RL adaptation | MSGI · Mining and Playground | normalized reward | Helped |
| Use explicit subtask graph inference and graph-conditioned execution instead of hierarchical RL | MSGI-GRProp · SC2LE | victory or success rate | Helped |
| Use explicit subtask graph inference and graph-conditioned execution instead of hierarchical RL or a random policy | MSGI-GRProp · AI2-THOR kitchen tasks | total reward | Helped |
| Train the adaptation policy with a meta-learning procedure rather than relying on an implicit recurrent adaptation scheme | RL² · Playground D2-D4 and Mining | normalized reward | Hurt |
Closest papers by meaning
- Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation (NeurIPS 2022 · similarity 0.91)
- AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers (NeurIPS 2024 · similarity 0.91)
- Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator (NeurIPS 2024 · similarity 0.90)
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (AAAI 2024 · similarity 0.90)
- DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning (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.