Validation of Double Transition Model by Analyzing Reward Distributions.

Eugene Santos Hien Nguyen Keum Joo Kim Gregory Hyde Clement Nyanhongo

Published in: WI/IAT (2020)

Keyphrases

transition model
reinforcement learning
reward function
probability distribution
state space
function approximation
random variables
markov decision problems
machine learning
decision making
markov chain
transition probabilities
temporal difference