Research map / Reinforcement learning / Policy gradient and actor-critic
Constrained Reinforcement Learning Has Zero Duality Gap
Santiago Paternain, Luiz Chamon, Miguel Calvo-Fullana, Alejandro Ribeiro
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 |
|---|---|---|---|
| Solve the primal maximization exactly rather than approximately | dualDescent on gridworld navigation · Gridworld navigation | duality gap | Improved |
| Replace exact primal maximization with a single policy-gradient step (ablation) | dualDescent on gridworld navigation · Gridworld navigation | duality gap | Hurt |
| Use a coarser state-aggregation parametrization (ablation) | Constrained RL policy on gridworld navigation · Gridworld navigation | duality gap | Hurt |
| Use a very coarse state-aggregation parametrization (ablation) | Constrained RL policy on gridworld navigation · Gridworld navigation | successful policy learning | Hurt |
Closest papers by meaning
- An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.88)
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.88)
- Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively (AAAI 2024 · similarity 0.88)
- DUO: Diverse, Uncertain, On-Policy Query Generation and Selection for Reinforcement Learning from Human Feedback (AAAI 2025 · similarity 0.88)
- To the Max: Reinventing Reward in Reinforcement Learning (ICML 2024 · similarity 0.87)
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.
