Robust Almost-Sure Reachability in Multi-Environment MDPs.

Marck van der Vegt Nils Jansen Sebastian Junges

Published in: CoRR (2023)

Keyphrases

state space
markov decision processes
mobile robot
machine learning
real time
reinforcement learning
dynamic environments
dynamic programming
planning under uncertainty
multi agent
virtual world
partial occlusion
complex environments
reward function