A Parallel Solver for Markov Decision Process in Crowd Simulations.

Sergio Ruiz Benjamín Hernández

Published in: MICAI (Special Sessions) (2015)

Keyphrases

markov decision process
state space
markov decision processes
optimal policy
reinforcement learning
finite horizon
temporal difference learning
transition matrices
infinite horizon
initial state
policy iteration
partial observability
learning algorithm
dynamic programming
reward function
average cost