Controllable Summarization with Constrained Markov Decision Process.

Hou Pong Chan Lu Wang Irwin King

Published in: CoRR (2021)

Keyphrases

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