Login / Signup
Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning.
Philippe Hansen-Estruch
Amy Zhang
Ashvin Nair
Patrick Yin
Sergey Levine
Published in:
ICML (2022)
Keyphrases
</>
reinforcement learning
state space
real world
markov decision processes
database
information systems
function approximation
temporal difference
reinforcement learning algorithms
neural network
genetic algorithm
search space
computational model
semantic relations
robotic control