Research map / Optimization / Nonconvex and smooth optimization
Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games
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 |
|---|---|---|---|
| Decentralized (each player keeps own critic, no access to other player's actions) single-timescale actor-critic with linear function approximation | zero-sum two-player stochastic games · theoretical analysis (no experiments) | optimality gap L(K) rate in K | No clear effect |
| Off-policy reuse of the same data batch instead of fresh batches each iteration | decentralized linear actor critic · theoretical sample complexity | sample complexity to reach Nash equilibrium: O(1/ε^4) to O(1/ε^2) | Helped |
Closest papers by meaning
- A Natural Actor-Critic Framework for Zero-Sum Markov Games (ICML 2022 · similarity 0.92)
- On the Convergence of Single-Timescale Actor-Critic (NeurIPS 2025 · similarity 0.89)
- Two-Timescale Critic-Actor for Average Reward MDPs with Function Approximation (AAAI 2025 · similarity 0.88)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.88)
- Solving Zero-Sum Markov Games with Continuous State via Spectral Dynamic Embedding (NeurIPS 2024 · similarity 0.87)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · 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.