Planning and Learning for Decentralized MDPs With Event Driven Rewards.

Tarun Gupta Akshat Kumar Praveen Paruchuri

Published in: AAAI (2018)

Keyphrases

event driven
reinforcement learning
markov decision processes
learning process
stochastic domains
learning algorithm
action selection
partially observable
database
peer to peer
planning problems
domain independent
blocks world
bandit problems
macro actions