Research map / Reinforcement learning / MDPs and planning
Sample Complexity of Variance-Reduced Distributionally Robust Q-Learning
Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
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 |
|---|---|---|---|
| add variance reduction to DR Q-learning (ablation) | DR Q-learning · Hard 4-state MDP, gamma 0.93 and 0.95, delta 0.1 | averaged infinity-norm error of q-function | Improved |
| variance-reduced DR Q-learning versus MLMC DR Q-learning | DR Q-learning · Hard MDP, gamma 0.6 and 0.7 | averaged error of q-function | Improved |
| DR Q-learning versus MLMC DR Q-learning | DR Q-learning · Hard MDP, gamma 0.6 and 0.7 | averaged error of q-function | Mixed |
| run proposed algorithms outside the limited-adversary regime (delta 0.1, gamma 0.93 or 0.95) | DR Q-learning and variance-reduced variant · Hard 4-state MDP | convergence rate | No clear effect |
| decrease adversary power delta toward 0 | variance-reduced DR Q-learning · Two-state DRMDP family | samples needed for fixed error: insensitive when delta <= 10^-2 | No clear effect |
Closest papers by meaning
- Near-Optimal Distributionally Robust Reinforcement Learning with General $L_p$ Norms (NeurIPS 2024 · similarity 0.90)
- Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning (NeurIPS 2025 · 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 0.89)
- Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model (NeurIPS 2024 · similarity 0.89)
- Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge (AAAI 2024 · similarity 0.88)
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.
