Corruption Robust Exploration in Episodic Reinforcement Learning.

Thodoris Lykouris Max Simchowitz Aleksandrs Slivkins Wen Sun

Published in: CoRR (2019)

Keyphrases

reinforcement learning
robust estimation
action selection
function approximation
learning process
multi agent
parameter tuning
active exploration
real time
data mining
genetic algorithm
markov decision processes