Robust Almost-Sure Reachability in Multi-Environment MDPs.

Marck van der Vegt Nils Jansen Sebastian Junges

Published in: TACAS (1) (2023)

Keyphrases

state space
markov decision processes
reinforcement learning
environmental conditions
robust estimation
noisy environments
decision making
partial occlusion
mobile robot
dynamic environments
autonomous agents
optimal policy
computationally efficient
data sets
search space
face recognition
e learning
neural network