Opponent Modelling in the Game of Tron using Reinforcement Learning.
Stefan J. L. KnegtMadalina M. DruganMarco A. WieringPublished in: ICAART (2) (2018)
Keyphrases
- reinforcement learning
- imperfect information
- computer poker
- game theory
- function approximation
- game theoretic
- human players
- game playing
- game play
- computer games
- video games
- game tree
- reinforcement learning algorithms
- model free
- game design
- temporal difference
- perfect information
- multi agent
- machine learning
- state space
- nash equilibrium
- serious games
- optimal control
- temporal difference learning
- monte carlo tree search
- virtual world
- educational games
- learning process
- reinforcement learning agents
- markov decision processes
- role playing
- learning algorithm
- robotic control
- multiagent reinforcement learning
- multi agent reinforcement learning
- mobile games
- reinforcement learning methods
- stochastic games
- nash equilibria