Deep Reinforcement Learning for 5 ˟ 5 Multiplayer Go.
Brahim DrissJérôme ArjonillaHui WangAbdallah SaffidineTristan CazenavePublished in: EvoApplications@EvoStar (2013)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- optimal policy
- temporal difference
- model free
- learning algorithm
- computer games
- supervised learning
- temporal difference learning
- deep learning
- machine learning
- educational games
- robot control
- online game
- imperfect information
- real time
- relational reinforcement learning
- partially observable
- action selection
- serious games
- learning problems
- state space
- mobile robot
- neural network