Research map / Reinforcement learning / Visual and representation RL
Learning Action Translator for Meta Reinforcement Learning on Sparse-Reward Tasks
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 action translation for transferring a source policy to the target task | Transferred policy on HalfCheetah · HalfCheetah | episode reward: 2355.0 -> 2937.2 | Helped |
| Add action translation for transferring a source policy to the target task | Transferred policy on Ant · Ant | episode reward: 55.8 -> 208.1 | Helped |
| Add action translation for transferring a source policy to the target task | Transferred policy on Cylinder-Mug · Cylinder-Mug | episode reward: 0.0 -> 395.6 | Helped |
| Add action translation for transferring a source policy to the target task | Transferred policy on Cylinder-Cube · Cylinder-Cube | episode reward: 0.0 -> 446.1 | Helped |
| Add policy transfer to context-based meta-RL | MCAT versus context-based baselines · Hopper Size, HalfCheetah Armature, HalfCheetah Mass, Ant Damp, Ant Cripple | test reward: MCAT: 1914.8, 2071.5, 1771.1, 624.6, 281.6 | Helped |
| Add policy transfer (ablation) | MCAT · Hopper Size | test reward: 1497.5 -> 1982.1 | Helped |
| Add policy transfer (ablation) | MCAT · HalfCheetah Armature | test reward: 579.1 -> 1776.8 | Helped |
| Add policy transfer (ablation) | MCAT · HalfCheetah Mass | test reward: -364.3 -> 67.1 | Helped |
| Add policy transfer (ablation) | MCAT · Ant Damp | test reward: 187.7 -> 211.8 | Helped |
| Add policy transfer (ablation) | MCAT · Ant Cripple | test reward: 92.4 -> 155.7 | Helped |
| Add policy transfer (ablation) | MCAT · HalfCheetah Armature, delay 200 | test reward: 2583.2 -> 2251.8 | Hurt |
| Add policy transfer (ablation) | MCAT · HalfCheetah Armature, delay 350 and 500; HalfCheetah Mass, delay 350 and 500 | test reward: 1771.7 -> 2004.5; 579.1 -> 1776.8; 156.6 -> 247.8; -364.2 -> 67.1 | Helped |
Closest papers by meaning
- Enhanced Meta Reinforcement Learning via Demonstrations in Sparse Reward Environments (NeurIPS 2022 · similarity 0.93)
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (AAAI 2024 · similarity 0.92)
- 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 0.91)
- Meta-Reinforcement Learning via Exploratory Task Clustering (AAAI 2024 · similarity 0.91)
- MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning (ICLR 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.