Scalable Deep Reinforcement Learning Algorithms for Mean Field Games.
Mathieu LaurièreSarah PerrinSertan GirginPaul MullerAyush JainTheophile CabannesGeorgios PiliourasJulien PérolatRomuald ÉlieOlivier PietquinMatthieu GeistPublished in: CoRR (2022)
Keyphrases
- reinforcement learning algorithms
- stochastic games
- reinforcement learning
- state space
- model free
- markov decision processes
- temporal difference
- reinforcement learning problems
- eligibility traces
- reinforcement learning methods
- learning algorithm
- function approximation
- reward function
- nash equilibria
- policy search
- markov random field
- game theory
- game playing
- multiagent reinforcement learning
- nash equilibrium
- dynamic environments
- em algorithm
- markov networks
- monte carlo
- bayesian inference
- fixed point
- least squares
- dynamic programming
- prior knowledge
- search algorithm
- reward shaping