Distributed Hybrid Kalman Temporal Differences for Reinforcement Learning.
Mohammad SalimibeniParvin MalekzadehArash MohammadiKonstantinos N. PlataniotisPublished in: ACSSC (2020)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- td learning
- evaluation function
- monte carlo
- model free
- multi agent
- policy iteration
- step size
- policy evaluation
- action selection
- temporal difference methods
- function approximators
- markov decision processes
- optimal policy
- state space
- learning algorithm
- supervised learning
- dynamic programming
- cost function
- reinforcement learning methods
- continuous state
- feature extraction
- neural network