No-Regret Reinforcement Learning with Heavy-Tailed Rewards.

Vincent Zhuang Yanan Sui

Published in: AISTATS (2021)

Keyphrases

heavy tailed
reinforcement learning
reward function
total reward
markov decision processes
reinforcement learning algorithms
state space
bandit problems
generalized gaussian
optimal policy
heavy tails
reward signal
learning algorithm
machine learning
probabilistic model
average reward