Research map / Reinforcement learning / Policy gradient and actor-critic
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
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 actor-critic variants (QPG, RPG, RMPG) instead of A2C in self-play | multiagent actor-critic · 2-player Leduc poker | NashConv | Helped |
| Use RPG/QPG actor-critic instead of NFSP | multiagent actor-critic · 2-player Leduc poker | NashConv | No clear effect |
| Use QPG/RPG instead of A2C against fixed CFR500 bots | multiagent actor-critic · Leduc poker vs CFR500 | mean reward | Helped |
| Use QPG/RPG current policy instead of NFSP average policy against fixed bots | multiagent actor-critic · Leduc poker vs CFR500 | mean reward | Helped |
| Use RMPG instead of RPG/QPG | multiagent actor-critic · Kuhn and Leduc poker | NashConv | Hurt |
Closest papers by meaning
- A Natural Actor-Critic Framework for Zero-Sum Markov Games (ICML 2022 · similarity 0.90)
- Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game (ICLR 2022 · similarity 0.90)
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.89)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.89)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.88)
- A Theoretical Justification for Asymmetric Actor-Critic Algorithms (ICML 2025 · similarity 0.88)
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.