Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning.
Jerin Paul SelvanPravin S. GamePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- game playing
- computer games
- temporal difference
- temporal difference learning
- imperfect information
- board game
- card game
- function approximation
- game players
- multi player
- games played
- online game
- pac man
- video games
- human players
- computer poker
- game theory
- evaluation function
- two player games
- game design
- monte carlo tree search
- game play
- perfect information
- game theoretic
- card games
- game based learning
- game tree search
- minimax search
- reinforcement learning algorithms
- educational games
- supervised learning
- machine learning
- serious games
- markov decision processes
- state space
- multi agent
- model free
- dynamic programming
- markov decision process
- general game playing
- optimal policy
- monte carlo
- learning algorithm
- playing games
- learning environment
- robotic control
- opponent modeling
- multi agent reinforcement learning
- optimal control
- game tree
- stochastic games
- digital games