Efficient Exploration for Constrained MDPs.

Majid Alkaee Taleghan Thomas G. Dietterich

Published in: AAAI Spring Symposia (2018)

Keyphrases

markov decision processes
reinforcement learning
optimal policy
state space
neural network
dynamic programming
factored mdps
decision diagrams
average cost
policy iteration
constrained problems
state and action spaces
data sets
average reward
finite horizon
finite state
linear programming
decision making