A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment.

Felix Leibfried Sergio Pascual-Diaz Jordi Grau-Moya

Published in: CoRR (2019)

Keyphrases

reinforcement learning
optimal solution
linear program
average reward
special case
long run
database
real world
decision making
bayesian networks
search algorithm
state space