Research map / Reinforcement learning / Visual and representation RL
Information-theoretic Task Selection for Meta-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 |
|---|---|---|---|
| Select relevant and sufficiently different training tasks using ITTS | RL² · CartPole | return | Helped |
| Select relevant and sufficiently different training tasks using ITTS | RL² · MiniGrid | return | Helped |
| Select relevant and sufficiently different training tasks using ITTS | MAML · Ant | return | Helped |
| Select relevant and sufficiently different training tasks using ITTS | MAML · Cheetah | return | Helped |
| Select relevant and sufficiently different training tasks using ITTS | RL² · Krazy World | return | Helped |
| Select relevant and sufficiently different training tasks using ITTS | RL² · MGEnv | return | Helped |
| Add task-difference filtering to relevance-based selection (ablation) | ITTS with relevance-only selection · CartPole | return | Helped |
| Add relevance filtering to difference-based selection (ablation) | ITTS with difference-only selection · CartPole | return | Helped |
| Add task-difference filtering to relevance-based selection (ablation) | ITTS with relevance-only selection · MiniGrid | return | Helped |
| Add relevance filtering to difference-based selection (ablation) | ITTS with difference-only selection · MiniGrid | return | Helped |
| Use a larger training task set rather than selecting tasks | Meta-RL · Transfer results across domains | return | Hurt |
Closest papers by meaning
- 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 0.90)
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (AAAI 2024 · similarity 0.90)
- Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Meta-Reinforcement Learning via Exploratory Task Clustering (AAAI 2024 · similarity 0.89)
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.