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