Research map / Reinforcement learning / MDPs and planning
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based 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 |
|---|---|---|---|
| Plan against the worst-case evolution allowed by Lipschitz bounds instead of optimizing for the current snapshot | RATS · Non-Stationary bridge | CVaR at 5% | Helped |
| Plan against worst-case evolution rather than the current snapshot | RATS · Non-Stationary bridge across ε values | discounted return | Mixed |
| Optimize expected return under the current snapshot rather than account for future model evolution | DP-snapshot · Non-Stationary bridge across ε values | discounted return | Mixed |
| Use expected-return optimization with access to the true NSMDP model instead of a worst-case objective | DP-NSMDP · Non-Stationary bridge | CVaR at 5% | Hurt |
Closest papers by meaning
- Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism (ICML 2020 · similarity 0.90)
- Acting in Delayed Environments with Non-Stationary Markov Policies (ICLR 2021 · similarity 0.90)
- DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees (NeurIPS 2026 · similarity 0.89)
- MetaCURL: Non-stationary Concave Utility Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- Pausing Policy Learning in Non-stationary Reinforcement Learning (ICML 2024 · similarity 0.88)
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games (ICML 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.