Self-play reinforcement learning with comprehensive critic in computer games.
Shanqi LiuJunjie CaoYujie WangWenzhou ChenYong LiuPublished in: Neurocomputing (2021)
Keyphrases
- computer games
- reinforcement learning
- function approximation
- actor critic
- reinforcement learning algorithms
- online game
- temporal difference
- game developers
- game playing
- board game
- quest atlantis
- policy gradient
- game design
- state space
- video games
- human players
- model free
- commercial games
- game play
- games based learning
- learning algorithm
- optimal control
- serious games
- game development
- educational software
- function approximators
- markov decision processes
- optimal policy
- empirical evidence
- reward function
- action selection