Research map / Reinforcement learning / Visual and representation RL
Factored Adaptation for Non-Stationary Reinforcement Learning
Fan Feng, Biwei Huang, Kun Zhang, Sara Magliacane
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| remove factored representation (binary masks/structure) (ablation) | FANS-RL · Half-Cheetah ablation | average return | Improved |
| add state prediction (ablation) | FANS-RL · Half-Cheetah ablation | average return | Improved |
| add reward prediction (ablation) | FANS-RL · Half-Cheetah with non-stationary reward | average return | Improved |
| add smoothness loss (ablation) | FANS-RL · Half-Cheetah within-episode changes | average return | Improved |
| use disentangled CF inference networks (ablation) | FANS-RL · Half-Cheetah dynamics and reward changes | average return | Improved |
| use FANS-RL instead of ZeUS, Meld, CaDM, Hyper-Dynamics | FANS-RL · Sawyer-Peg raw pixels | average return: 12.45 -> 18.01 | Improved |
| increase non-stationarity degree | FANS-RL · Half-Cheetah | average return | Improved |
| use fewer latent dimensions | FANS-RL · Half-Cheetah | average return | Improved |
| add multiple concurrent change factors (1D to 2D+1R) | FANS-RL · Half-Cheetah | average return | Improved |
| vary functional form (piecewise linear, damped, sine) | FANS-RL · Half-Cheetah | average return | Improved |
Closest papers by meaning
- Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation (ICML 2024 · similarity 0.90)
- Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations (ICLR 2025 · similarity 0.89)
- Forecasting in Offline Reinforcement Learning for Non-stationary Environments (NeurIPS 2025 · similarity 0.87)
- Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning (ICML 2024 · similarity 0.87)
- DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees (NeurIPS 2026 · similarity 0.86)
- Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset (NeurIPS 2024 · similarity 0.86)
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.
