Research map / Reinforcement learning / Visual and representation RL
AdaRL: What, Where, and How to Adapt in Transfer 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 |
|---|---|---|---|
| Learn structural masks rather than assume a fully connected graph (ablation) | AdaRL · Modified Cartpole MDP, G_in | final score: 1940.5 -> 2217.6 | Helped |
| Learn structural masks rather than assume a fully connected graph (ablation) | AdaRL · Modified Cartpole POMDP, N_in | final score: 5540.8 -> 7817.4 | Helped |
| Learn structural masks rather than assume a fully connected graph (ablation) | AdaRL · Modified Pong POMDP, S_out | final score: 12.80 -> 17.82 | Helped |
| Use AdaRL instead of the strongest listed baseline, PSM | Modified Pong POMDP · C_in | final score: 19.02 -> 19.14 | No clear effect |
| Use AdaRL rather than MTQ | Modified Cartpole POMDP · G_out | final score: 330.6 -> 353.4 | Helped |
| Use AdaRL rather than MTQ | Modified Pong POMDP · N_out | final score: 15.77 -> 18.30 | Helped |
Closest papers by meaning
- Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations (ICLR 2025 · similarity 0.87)
- Cross-Domain Policy Adaptation by Capturing Representation Mismatch (ICML 2024 · similarity 0.87)
- AdaCuRL: Adaptive Curriculum Reinforcement Learning with Invalid Sample Mitigation and Historical Revisiting (AAAI 2026 · similarity 0.87)
- BlendRL: A Framework for Merging Symbolic and Neural Policy Learning (ICLR 2025 · similarity 0.87)
- Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder (AAAI 2025 · similarity 0.87)
- Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning (ICLR 2025 · similarity 0.87)
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.