Counterexample Guided RL Policy Refinement Using Bayesian Optimization.
Briti GangopadhyayPallab DasguptaPublished in: NeurIPS (2021)
Keyphrases
- optimal policy
- reinforcement learning
- optimization method
- optimization algorithm
- bayesian networks
- markov decision process
- optimization process
- global optimization
- learning algorithm
- action space
- multi agent
- model checking
- optimization problems
- action selection
- markov decision processes
- maximum likelihood
- function approximation
- evolutionary algorithm
- constrained optimization
- partially observable
- neural network
- control policy
- policy search
- state and action spaces
- partially observable domains