Neurosymbolic Reinforcement Learning with Formally Verified Exploration.

Greg Anderson Abhinav Verma Isil Dillig Swarat Chaudhuri

Published 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