State Action Separable Reinforcement Learning.
Ziyao ZhangLiang MaKin K. LeungKonstantinos PoularakisMudhakar SrivatsaPublished in: CoRR (2020)
Keyphrases
- state action
- reinforcement learning
- evaluation function
- function approximators
- function approximation
- action space
- stochastic games
- continuous state
- markov decision process
- state space
- reinforcement learning algorithms
- markov decision processes
- temporal difference
- average reward
- state transitions
- dynamic programming
- optimal policy
- model free
- partially observable
- policy gradient
- learning automata
- belief state
- neural network
- learning algorithm
- transfer learning
- supervised learning
- kernel matrix
- learning capabilities
- reward function
- optimal control
- real valued
- multi agent systems
- machine learning