Reinforcement Learning with History Dependent Dynamic Contexts.

Guy Tennenholtz Nadav Merlis Lior Shani Martin Mladenov Craig Boutilier

Published in: ICML (2023)

Keyphrases

reinforcement learning
multi agent
function approximation
real time
machine learning
information retrieval
website
multiscale
search space
hidden markov models
state space
dynamic environments
markov decision processes