Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning.

Philippe Hansen-Estruch Amy Zhang Ashvin Nair Patrick Yin Sergey Levine

Published in: CoRR (2022)

Keyphrases

reinforcement learning
multi agent
neural network
machine learning
markov decision processes
function approximation
learning algorithm
learning process
supervised learning
function approximators
information retrieval
dynamic programming
model free
reinforcement learning algorithms
stochastic approximation