Learning to Play Pac-Xon with Q-Learning and Two Double Q-Learning Variants.
Jits SchilperoortIvar MakMadalina M. DruganMarco A. WieringPublished in: SSCI (2018)
Keyphrases
- learning algorithm
- reinforcement learning
- cooperative
- action selection
- function approximation
- temporal difference learning
- multiagent learning
- state space
- reinforcement learning algorithms
- learning agent
- temporal difference methods
- reinforcement learning methods
- noise tolerant
- learning systems
- learning process
- e learning
- learning problems
- model free
- learning tasks
- efficient learning
- supervised learning
- upper bound
- mobile robot
- active learning
- multi agent reinforcement learning
- relational reinforcement learning
- credit assignment