A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment.

Felix Leibfried Sergio Pascual-Diaz Jordi Grau-Moya

Published in: NeurIPS (2019)

Keyphrases

database
reinforcement learning
optimal solution
average reward
real time
multiscale
search algorithm
expert systems
multi objective
combining multiple
inverse reinforcement learning