Research map / Bandits and online learning / RL theory and MDPs
Provably Efficient Model-Free Constrained RL with Linear Function Approximation
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 a soft-max policy instead of greedy action selection (ablation) | Primal-dual LSVI-UCB for linear CMDPs · Episodic linear CMDP | uniform concentration for individual value functions | Helped |
| Tighten the constraint by adding ζ (ablation) | Our approach · Episodic linear CMDP, sufficiently large T | constraint violation: 0 | Helped |
| Increase the soft-max temperature parameter α (ablation) | Primal-dual LSVI-UCB · Episodic linear CMDP | soft-max approximation error to greedy value: K\dfrac{H\log(|\mathcal A|)}{\alpha} | Helped |
Closest papers by meaning
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation (NeurIPS 2025 · similarity 0.91)
- Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds (ICLR 2025 · similarity 0.90)
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.89)
- Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively (AAAI 2024 · similarity 0.89)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.89)
- Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces (ICML 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.