Neurosymbolic Reinforcement Learning with Formally Verified Exploration.
Greg AndersonAbhinav VermaIsil DilligSwarat ChaudhuriPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- exploration strategy
- active exploration
- action selection
- exploration exploitation
- model based reinforcement learning
- function approximation
- reinforcement learning algorithms
- autonomous learning
- state space
- robotic control
- exploration exploitation tradeoff
- model free
- learning algorithm
- machine learning
- markov decision processes
- policy search
- data mining
- multi agent
- temporal difference learning
- learning agents
- interactive exploration
- control problems
- temporal difference
- monte carlo
- dynamic environments
- evolutionary algorithm
- direct policy search
- neural network