Constrained Deep Q-Learning Gradually Approaching Ordinary Q-Learning.
Shota OhnishiEiji UchibeYotaro YamaguchiKosuke NakanishiYuji YasuiShin IshiiPublished in: Frontiers Neurorobotics (2019)
Keyphrases
- reinforcement learning
- function approximation
- cooperative
- multi agent
- state space
- learning algorithm
- stochastic approximation
- learning rate
- model free
- optimal policy
- temporal difference learning
- reinforcement learning algorithms
- multi agent reinforcement learning
- action selection
- td learning
- bucket brigade
- data sets
- learning agent
- deep learning
- monte carlo
- multiagent learning
- potential field
- case study
- neural network
- real time
- credit assignment