Deep Reinforcement Learning for 5*5 Multiplayer Go.
Brahim DrissJérôme ArjonillaHui WangAbdallah SaffidineTristan CazenavePublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- learning algorithm
- state space
- machine learning
- educational games
- computer games
- markov decision processes
- online game
- temporal difference learning
- model free
- multi agent
- dynamic programming
- multi agent reinforcement learning
- reinforcement learning methods
- relational reinforcement learning
- deep learning
- serious games
- policy search
- belief nets
- robot control
- robotic control
- partially observable
- learning capabilities
- action selection
- real time
- optimal control
- hidden markov models
- learning process
- search algorithm
- real world