Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs.

Jianzhun Du Joseph Futoma Finale Doshi-Velez

Published in: CoRR (2020)

Keyphrases

model based reinforcement learning
semi markov decision processes
markov decision processes
average reward
state space
reinforcement learning
optimal policy
finite state
policy iteration
dynamic programming
partially observable
decision processes
multi agent
markov decision process
infinite horizon