Research map / Reinforcement learning / MDPs and planning
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
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 conservative constraints with a positive κ | CSPDA · CMDP | constraint violation: 0 | Helped |
| Use conservative constraints with a positive κ rather than κ = 0 (ablation) | CSPDA · Queueing System | constraint value | Helped |
| Use conservative constraints with a positive κ rather than κ = 0 (ablation) | CSPDA · Queueing System | cumulative reward | No clear effect |
| Use CSPDA instead of Triple-Q for zero-violation CMDP learning | CMDP · CMDP (theoretical comparison) | sample complexity: \tdO\bigg(\frac{|\ccalS|^{2.5}|\ccalA|^{2.5}}{(1-\gamma)^{18.5}\epsilon^5}\bigg) vs. \tdO\bigg(\frac{|\ccalS||\ccalA|}{( | Helped |
| Set the conservative parameter κ to 0 instead of choosing a positive value (ablation) | CSPDA · CMDP | constraint violation: -\epsilon vs. 0 | Hurt |
Closest papers by meaning
- Truly No-Regret Learning in Constrained MDPs (ICML 2024 · similarity 0.92)
- Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process (NeurIPS 2024 · similarity 0.91)
- Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm (NeurIPS 2024 · similarity 0.91)
- Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm (NeurIPS 2025 · similarity 0.90)
- Sample-Efficient Constrained Reinforcement Learning with General Parameterization (NeurIPS 2024 · similarity 0.90)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.89)
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.