Research map / Reinforcement learning / Offline RL
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
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 pessimistic critic estimates with actor mirror descent | PACLE · Offline RL, arbitrary comparator policy | suboptimality gap: 4 \horizon \sqrt{\tfrac{\log |\ActionSpace|}{\actortot}} | Helped |
| Compare against any well-covered near-optimal policy, rather than only the optimal policy | PACLE · Offline RL, arbitrary comparator policy | suboptimality gap | Helped |
| Perturb linear critic parameters directly to implement pessimism, preserving linear value functions | PACLE · Offline RL with linear function approximation | statistical estimation error bound: sharper by a factor of \sqrt{d} | Helped |
| Use Bellman restricted closedness instead of requiring a low-rank MDP | PACLE · Offline RL | applicable MDP class | Helped |
| Apply the uncertainty term based on data coverage | PACLE · Offline RL, low-rank MDPs | expected suboptimality gap lower bound: c \; \Uncertain(\pi; \sqrt{d}) | Mixed |
Closest papers by meaning
- Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning (NeurIPS 2023 · similarity 0.94)
- Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Offline Actor-Critic Reinforcement Learning Scales to Large Models (ICML 2024 · similarity 0.90)
- Actor-Critics Can Achieve Optimal Sample Efficiency (ICML 2025 · similarity 0.90)
- A Theoretical Justification for Asymmetric Actor-Critic Algorithms (ICML 2025 · similarity 0.89)
- Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning (AAAI 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.