NeuroHex: A Deep Q-learning Hex Agent.
Kenny YoungGautham VasanRyan HaywardPublished in: CGW@IJCAI (2016)
Keyphrases
- multi agent
- action selection
- multi agent systems
- reinforcement learning
- learning agent
- multiagent systems
- cooperative
- intelligent agents
- single agent
- autonomous agents
- agent receives
- state action
- agent model
- software agents
- decision making
- state space
- agent technology
- reward function
- optimal policy
- model free
- game playing
- learning algorithm
- agent architecture
- multiple agents
- decision theoretic
- evaluation function
- mobile agents
- multi agent reinforcement learning
- function approximation
- learning capabilities
- agent systems
- temporal difference learning
- game tree search
- multiagent learning