Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes.

Eoin M. Kenny Mycal Tucker Julie Shah

Published in: ICLR (2023)

Keyphrases

human friendly
reinforcement learning
function approximation
learning algorithm
state space
machine learning
multi agent
markov decision processes
model free
context aware
data mining
artificial intelligence
fuzzy logic
optimal policy
social intelligence