Decentralized Single-Timescale Actor-Critic on Zero-Sum Two-Player Stochastic Games

Authors: Hongyi Guo, Zuyue Fu, Zhuoran Yang, Zhaoran Wang

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the global convergence and global optimality of the actor-critic algorithm applied for the zero-sum two-player stochastic games in a decentralized manner. We prove that the sequence of joint policy generated by our decentralized linear algorithm converges to the minimax equilibrium at a sublinear rate O(K), where K is the number of iterations. To the best of our knowledge, we establish the global optimality and convergence of our decentralized actor-critic algorithm on zero-sum two-player stochastic games with linear function approximations for the first time.
Researcher Affiliation Academia 1Northwestern University 2Princeton University.
Pseudocode Yes Algorithm 1 Decentralized Actor Critic on Zero-Sum Two-Player Stochastic Games
Open Source Code No The paper does not provide any statements about open-sourcing code or links to repositories.
Open Datasets No The paper focuses on theoretical analysis and does not mention using specific datasets for training or their availability.
Dataset Splits No The paper focuses on theoretical analysis and does not describe any training, validation, or test dataset splits.
Hardware Specification No The paper focuses on theoretical analysis and does not mention any specific hardware used for experiments.
Software Dependencies No The paper focuses on theoretical analysis and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper focuses on theoretical analysis and does not describe any experimental setup details such as hyperparameters or training configurations.