Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning.
Julien PérolatBart De VylderDaniel HennesEugene TarassovFlorian StrubVincent de BoerPaul MullerJerome T. ConnorNeil BurchThomas W. AnthonyStephen McAleerRomuald ElieSarah H. CenZhe WangAudrunas GruslysAleksandra MalyshevaMina KhanSherjil OzairFinbarr TimbersToby PohlenTom EcclesMark RowlandMarc LanctotJean-Baptiste LespiauBilal PiotShayegan OmidshafieiEdward LockhartLaurent SifreNathalie BeauguerlangeRémi MunosDavid SilverSatinder SinghDemis HassabisKarl TuylsPublished in: CoRR (2022)
Keyphrases
- model free
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov games
- stochastic games
- reinforcement learning
- average reward
- joint action
- function approximation
- temporal difference
- multiagent systems
- multi agent
- policy iteration
- cooperative
- nash equilibrium
- markov decision processes
- dynamic environments
- game playing
- single agent
- markov decision process
- learning agent
- state space