Softened Approximate Policy Iteration for Markov Games
By Julien Pérolat, Bilal Piot, Matthieu Geist, Bruno Scherrer, Olivier Pietquin. 2016
43 citations recorded by the source corpus.
Subfields: Reinforcement Learning, Game & Decision Theory
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Sergey Levine
- Zhuoran Yang
- Yuxi Li
- R´emi Munos
- Karl Tuyls
- Olivier Pietquin
- Marc Lanctot
- Pieter Abbeel
In Game & Decision Theory
- Karl Tuyls
- Zhuoran Yang
- Julien Pérolat
- Thore Graepel
- Marc Lanctot
- Joel Z. Leibo
- Jean-Baptiste Lespiau
- David Balduzzi
Citations in the corpus
- OpenSpiel: A Framework for Reinforcement Learning in Games (2019, background): “Game Reference(s) Status Backgammon Wikipedia Breakthrough Wikipedia Bridge bidding Wikipedia Coin Game [56] ∼ Connect Four Wikipedia Cooperative Box-Pushing [62] ∼ Chess Wikipedia First-price Sealed-bid Auction Wikipedia Go Wikipedia Goofspiel Wikipedia Havannah Wikipedia Hex Wikipedia ∼ Kuhn poker”
- Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017, methodology): “Several algorithms and analyses have been developed for the two-player zero-sum case [22, 27, 28, 29, 30].”
- A Theoretical Analysis of Deep Q-Learning (2019, methodology): “We note that Pérolat et al. (2015) establish error propagation for the state-value functions in the approximate modified policy iteration algorithm, which is more general than the FQI algorithm.”
- Is the Bellman residual a bad proxy? (2016, methodology): “Projected Bellman residual approaches are more common, even if not introduced as such originally (notable exceptions are [16, 18]).”
- From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization (2020, background): “Generally speaking, in the sequential 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”
- Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium (2020, methodology): “eoretical results therein also require a sampling oracle, and they focus on turn-based games, a special case of simultaneous-move games. 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 t”