Stochastic Reinforcement in Evolutionary Multi-Agent Game Playing of Dots-and-Boxes.
Anthony KnittelTerry BossomaierMike HarréAllan SnyderPublished in: CIMCA/IAWTIC (2006)
Keyphrases
- game playing
- multi agent
- reinforcement learning
- temporal difference learning
- general game playing
- game tree search
- video games
- tic tac toe
- game tree
- monte carlo
- opponent modeling
- imperfect information
- game based learning
- multi player
- cooperative
- world class
- multi agent systems
- genetic algorithm
- game play
- black and white
- learning outcomes
- computer games
- software agents
- game players
- adventure game