Overcoming Model Bias for Robust Offline Deep Reinforcement Learning.

Phillip Swazinna Steffen Udluft Thomas A. Runkler

Published in: CoRR (2020)

Keyphrases

theoretical analysis
computational model
reinforcement learning
mathematical model
high level
probability distribution
statistical model
conceptual model
formal model
model free
probabilistic model
theoretical framework
data sets
social networks
markov chain