Research map / Reinforcement learning / MDPs and planning
Robust Average-Reward Markov Decision Processes
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 |
|---|---|---|---|
| Use robust methods instead of non-robust value iteration | Value iteration on Garnet problem G(20,40) · Garnet problem, contamination model (R=0.4) | robust average-reward | Helped |
| Use robust methods instead of non-robust value iteration | Value iteration on Garnet problem G(20,40) · Garnet problem, total variation model (R=0.6) | robust average-reward | Helped |
| Use robust methods instead of non-robust value iteration | Value iteration on Garnet problem G(20,40) · Garnet problem, KL-divergence model (R=0.8) | robust average-reward | Helped |
| Use limit-based robust value iteration or direct robust relative value iteration | Robust average-reward optimal control · Garnet problem, contamination, total variation, and KL-divergence models | robust average-reward | No clear effect |
Closest papers by meaning
- Policy Optimization for Robust Average Reward MDPs (NeurIPS 2024 · similarity 0.95)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.92)
- Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization (AAAI 2024 · similarity 0.91)
- Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity (ICML 2025 · similarity 0.91)
- Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
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.