On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games

By Julien Pérolat, Bilal Piot, Bruno Scherrer, Olivier Pietquin. 2016

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, background): “If an agent is inside the blue diamond-shaped region around the prey when a capture occurs—when one agent touches the prey—both it and its partner receive a reward of r team . cyclic strategy composed of several policies obtained through multiple state space sweeps [35].”
Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium (2020, methodology): “The work in Lagoudakis and Parr (2012); Perolat et al. (2015); Pérolat et al. (2016b,a,c); Yang et al. (2019) considers function approximation techniques applied to variants of value-iteration methods and establishes ﬁnite-time convergence to the NEs of two-player zero-sum Markov games.”
Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications (2018, methodology): “The general-sum modelling requires solving algorithms to either track different potential equilibria for each agent or be able to find cyclic strategy consisting of multiple policies learned by using different state space sweeps [122, 89].”
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments (2018, background): “Much work in classical MARL focuses on Markov games where the environment is fully observable and agents take actions simultaneously, which in some cases admit Bellman operators [55, 103, 70, 69].”
A Theoretical Analysis of Deep Q-Learning (2019, methodology): “When F is the family of neural networks, Algorithm 1 is known as the neural FQI, which is proposed in Riedmiller (2005). Thus, we can view neural FQI as an modification of DQN, where we replace experience replay by sampling from a fixed distribution σ, so as to understand its the statistical propert”
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization (2020, background): “…setting, learning in games can be addressed by either approximate dynamic programming in the perfect information case (Lagoudakis & Parr, 2002; Pérolat et al., 2015; 2016; Pérolat et al., 2016; 2017; Geist et al., 2019), regret minimization algorithms (Zinkevich et al., 2008; Lanctot, 2013;…”