Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity.
Wei LiaoXiaohui WeiJizhou LaiPublished in: CoRR (2021)
Keyphrases
- stochastic approximation
- reinforcement learning
- function approximation
- stochastic shortest path
- cooperative
- learning algorithm
- state space
- multi agent
- learning rate
- convergence rate
- model free
- convergence proof
- similarity measure
- multi agent reinforcement learning
- optimal policy
- action selection
- reinforcement learning algorithms
- credit assignment
- temporal difference learning
- neural network
- bucket brigade
- decision making
- reinforcement learning methods
- learning agent
- euclidean distance