Research map / Reinforcement learning / MDPs and planning
Semi-infinitely Constrained Markov Decision Processes
Liangyu Zhang, Yang Peng, Wenhao Yang, Zhihua Zhang
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 |
|---|---|---|---|
| increase dataset size m | SI-CRL · Toy SICMDP | error term | Improved |
| vary discount gamma and minimum measure nu_min | SI-CRL · Toy SICMDP | log sample complexity | No clear effect |
| increase state-space size |S| | SI-CRL · Discharge of Sewage | sample and iteration complexity | No clear effect |
| use SICMDP continuum of constraints instead of discretized CMDP baseline | SI-CRL · Discharge of Sewage | policy quality / constraint violation: T = Tbaseline = 9 | Improved |
| use SI-CRL (dual simplex re-optimization) instead of single-LP CMDP baseline | SI-CRL · Discharge of Sewage | time to reach given accuracy | Improved |
| use SI-CRL with adaptively added constraints instead of fixed-grid baseline | SI-CRL · Discharge of Sewage | number of active constraints for same accuracy | Improved |
| vary number of constraints T / Tbaseline | SI-CRL vs CMDP baseline · Discharge of Sewage | log(Error) | Improved |
Closest papers by meaning
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation (NeurIPS 2025 · similarity 0.90)
- Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process (NeurIPS 2024 · similarity 0.90)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 2024 · similarity 0.89)
- Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs (NeurIPS 2026 · similarity 0.89)
- Polynomial-Time Approximability of Constrained Reinforcement Learning (ICML 2025 · similarity 0.89)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · 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.
