Neural Distillation as a State Representation Bottleneck in Reinforcement Learning.

Valentin Guillet Dennis George Wilson Emmanuel Rachelson

Published in: CoLLAs (2022)

Keyphrases

reinforcement learning
state space
neural network
fitted q iteration
function approximation
supervised learning
feature representation
bio inspired
machine learning
multi agent
initial state
markov decision process
distributed representations
explicitly represent