Imitating Graph-Based Planning with Goal-Conditioned Policies.

Junsu Kim Younggyo Seo Sungsoo Ahn Kyunghwan Son Jinwoo Shin

Published in: ICLR (2023)

Keyphrases

macro actions
planning problems
reinforcement learning
stochastic domains
domain independent
markov decision problems
goal oriented
motion planning
interactive narrative
goal state
production planning
plan recognition
social networks
heuristic search
decision support
domain specific
information systems