Stochastic synapse reinforcement learning (SSRL).
Syed Naveed Hussain ShahDean F. HougenPublished in: SSCI (2017)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- function approximation
- control policies
- multi agent
- state space
- monte carlo
- learning algorithm
- partially observable
- control problems
- control policy
- markov decision processes
- optimal policy
- temporal difference
- reinforcement learning algorithms
- model free
- markov decision process
- learning rules
- reinforcement learning methods
- evaluation function
- autonomous learning
- continuous state spaces
- policy search
- model free reinforcement learning