Research map / Reinforcement learning / Visual and representation RL
Unsupervised Curricula for Visual 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 |
|---|---|---|---|
| refine task distribution over outer-loop iterations (reorganization) vs early iterations (ablation) | CARML · ViZDoom transfer | transfer success | Helped |
| use generative-discriminative mixture instead of purely online discriminator for task acquisition (ablation) | CARML · ViZDoom Random | direct transfer | Helped |
| pretrain discriminator encoder with CARML algorithm (online pretrained-discriminator) (ablation) | online discriminator · ViZDoom | task diversity / transfer | Helped |
| joint task acquisition and meta-learning instead of pipelined (ablation) | CARML · ViZDoom Random | transfer | Helped |
| finetune CARML meta-policy vs PPO from scratch | CARML · ViZDoom Random | sample efficiency | Helped |
| CARML pretraining as initialization for supervised meta-RL | RL2 · ViZDoom / Sawyer | sample efficiency | Helped |
Closest papers by meaning
- Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation (CVPR 2020 · similarity 0.91)
- Guided Meta-Policy Search (NeurIPS 2019 · similarity 0.91)
- Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills (AAAI 2024 · similarity 0.90)
- Skill-based Meta-Reinforcement Learning (ICLR 2022 · similarity 0.90)
- Meta-Reinforcement Learning via Exploratory Task Clustering (AAAI 2024 · similarity 0.90)
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics Components (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.