Mastering Fighting Game Using Deep Reinforcement Learning With Self-play.
Dae-Wook KimSungyun ParkSeong-Il YangPublished in: CoG (2020)
Keyphrases
- reinforcement learning
- game playing
- temporal difference learning
- imperfect information
- pac man
- online game
- american football
- game mechanics
- computer games
- games played
- function approximation
- game players
- multi player
- human players
- board game
- card game
- model free
- video games
- nash equilibrium
- minimax search
- game design
- game theory
- state space
- game based learning
- machine learning
- optimal policy
- game theoretic
- learning process
- multi agent
- game play
- educational games
- general game playing
- temporal difference
- evaluation function
- game tree search
- playing games
- neural network
- nash equilibria
- current status
- game tree
- transfer learning
- e learning
- quest atlantis
- dynamic programming
- game description language
- agent learns
- opponent modeling
- cooperative game
- learning experience
- markov decision processes
- learning agents
- game development
- function approximators
- reinforcement learning algorithms