Neurosymbolic Reinforcement Learning with Formally Verified Exploration.
Greg AndersonAbhinav VermaIsil DilligSwarat ChaudhuriPublished in: NeurIPS (2020)
Keyphrases
- reinforcement learning
- exploration strategy
- active exploration
- action selection
- model based reinforcement learning
- exploration exploitation
- function approximation
- markov decision processes
- robotic control
- autonomous learning
- reinforcement learning algorithms
- optimal policy
- temporal difference
- state space
- dynamic programming
- evolutionary algorithm
- multi agent
- machine learning
- control problems
- markov decision process
- temporal difference learning
- reinforcement learning methods
- stochastic approximation
- multi agent reinforcement learning
- policy search
- data analysis
- decision trees
- learning algorithm
- genetic algorithm