Research map / Reinforcement learning / Policy gradient and actor-critic
Better Exploration with Optimistic Actor Critic
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 OAC's optimistic exploration instead of SAC exploration | SAC · Humanoid-v2, 4 gradient steps per environment step | total undiscounted return: 4586 \pm 117 -> 5033 \pm 147 | Helped |
| use the bootstrapped uncertainty estimate for optimistic exploration rather than the approximate lower bound (ablation) | OAC · Humanoid | performance | Helped |
| use the bootstrapped uncertainty estimate for optimistic exploration rather than the approximate lower bound (ablation) | OAC · other MuJoCo domains | performance | Mixed |
| use a shifted exploration policy while retaining the KL constraint | OAC · MuJoCo continuous control | learning stability | No clear effect |
| use optimistic exploration | actor-critic methods · Ant | total undiscounted return | Helped |
| use optimistic exploration | actor-critic methods · Hopper | final performance | Helped |
| use optimistic exploration | actor-critic methods · Walker | performance | No clear effect |
| use optimistic exploration | actor-critic methods · HalfCheetah | performance | Mixed |
Closest papers by meaning
- Actor-Critics Can Achieve Optimal Sample Efficiency (ICML 2025 · similarity 0.92)
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL (NeurIPS 2025 · similarity 0.91)
- Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling (ICLR 2025 · similarity 0.91)
- Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning (AAAI 2025 · similarity 0.90)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.90)
- Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning (ICLR 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.