The Efficacy of Pessimism in Asynchronous Q-Learning.
Yuling YanGen LiYuxin ChenJianqing FanPublished in: CoRR (2022)
Keyphrases
- cooperative
- reinforcement learning
- function approximation
- state space
- multi agent
- learning algorithm
- multi agent reinforcement learning
- optimal policy
- learning rate
- stochastic approximation
- reinforcement learning algorithms
- model free
- data sets
- potential field
- dynamic programming
- information systems
- action selection
- expert systems
- reinforcement learning methods
- support vector
- bucket brigade
- database
- asynchronous communication
- discussion groups
- hierarchical reinforcement learning