Research map / Reinforcement learning / MDPs and planning
Online Robust Reinforcement Learning with Model Uncertainty
Yue Wang, Shaofeng Zou
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 |
|---|---|---|---|
| robust Q-learning instead of vanilla Q-learning, trained on perturbed MDP | Q-learning · FrozenLake-v0 and CartPole-v0 | accumulated discounted reward | Improved |
| larger perturbation p and radius R | robust Q-learning vs vanilla · FrozenLake-v0 and CartPole-v0 | accumulated discounted reward | Improved |
| robust TDC instead of vanilla TDC with linear function approximation | TDC · FrozenLake-v0 4x4 | squared gradient norm | Improved |
| robust TDC has smaller variance across 30 runs | TDC · FrozenLake-v0 4x4 | variance of gradient norm | Improved |
| robust Q-learning instead of RARL adversarial training | Q-learning · Taxi-v3 | accumulated discounted reward | Improved |
| robust Q-learning instead of RARL | Q-learning · Taxi-v3 | training variance | Improved |
Closest papers by meaning
- Time-Constrained Robust MDPs (NeurIPS 2024 · similarity 0.92)
- Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Model-Free Robust $\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data (ICML 2024 · similarity 0.90)
- Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (NeurIPS 2024 · similarity 0.90)
- Single-Trajectory Distributionally Robust Reinforcement Learning (ICML 2024 · similarity 0.90)
- Robust Offline Reinforcement Learning with Linearly Structured $f$-Divergence Regularization (ICML 2025 · 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.
