Research map / Reinforcement learning / Offline RL
Importance Weighted Actor-Critic for Optimal Conservative 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 an importance-weighted average Bellman error regularizer instead of a squared Bellman-error regularizer | A-Crab · Offline RL, any covered policy | suboptimality rate: O(1/N^{1/3}) -> O \left(\frac{1}{\sqrt{N}}\right) | Helped |
| Replace the importance-weighted average Bellman error regularizer with squared Bellman error (ablation) | A-Crab · Constructed two-arm bandit | suboptimality: \Omega(1/N^{1/3}) | Hurt |
| Use squared Bellman error rather than importance-weighted average Bellman error (ablation) | A-Crab · Offline RL, constructed instances | suboptimality rate: O(1/N^{1/3}) | Hurt |
Closest papers by meaning
- Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL (ICML 2024 · similarity 0.90)
- Actor-Critics Can Achieve Optimal Sample Efficiency (ICML 2025 · similarity 0.90)
- Offline Actor-Critic Reinforcement Learning Scales to Large Models (ICML 2024 · similarity 0.90)
- Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning (ICML 2024 · similarity 0.90)
- Bayesian Design Principles for Offline-to-Online Reinforcement Learning (ICML 2024 · similarity 0.90)
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.