Research map / Reinforcement learning / Policy gradient and actor-critic
Constrained episodic reinforcement learning in concave-convex and knapsack settings
Kianté Brantley, Miro Dudik, Thodoris Lykouris, Sobhan Miryoosefi, Max Simchowitz, Aleksandrs Slivkins, Wen Sun
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 |
|---|---|---|---|
| Use ConRL with value iteration as the planner | Constrained episodic RL · Mars rover | trajectories needed to solve the constrained task | Improved |
| Use ConRL with A2C as the planner | Constrained episodic RL · Mars rover | trajectories needed to solve the constrained task | Improved |
| Use ConRL with value iteration as the planner | Constrained episodic RL · Box | trajectories needed to solve the constrained task | Improved |
| Use ConRL with A2C as the planner | Constrained episodic RL · Box | trajectories needed to solve the constrained task | Improved |
| Use ConRL rather than ApproPO | Constrained episodic RL · Mars rover | cumulative consumption | Improved |
| Use ConRL rather than RCPO | Constrained episodic RL · Mars rover | cumulative consumption | Improved |
| Use ConRL rather than ApproPO | Constrained episodic RL · Box | cumulative consumption | Improved |
| Use ConRL rather than RCPO | Constrained episodic RL · Box | cumulative consumption | Improved |
| Use ConRL rather than TFW-UCRL2 | Constrained episodic RL · Mars rover | trajectories needed to find a solution | Improved |
| Use ConRL rather than TFW-UCRL2 | Constrained episodic RL · Mars rover | consumption | Improved |
Closest papers by meaning
- e-COP : Episodic Constrained Optimization of Policies (NeurIPS 2024 · similarity 0.89)
- A Simple Reward-free Approach to Constrained Reinforcement Learning (ICML 2022 · similarity 0.88)
- Online Reinforcement Learning with Uncertain Episode Lengths (AAAI 2023 · similarity 0.87)
- Reinforcement Learning with Convex Constraints (NeurIPS 2019 · similarity 0.87)
- Online Episodic Convex Reinforcement Learning (ICML 2025 · similarity 0.86)
- DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees (NeurIPS 2026 · similarity 0.85)
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.
