MAGIC: Learning Macro-Actions for Online POMDP Planning using Generator-Critic.

Yiyuan Lee Panpan Cai David Hsu

Published in: CoRR (2020)

Keyphrases

macro actions
reinforcement learning
markov decision processes
learning process
state space
partially observable
planning domains
neural network
dynamic programming
domain independent
planning problems
machine learning
learning mechanism
planning under uncertainty