Reinforcement Learning with Multiple Shared Rewards.
Douglas M. GuisiRichardson RibeiroMarcelo TeixeiraAndré Pinz BorgesFabrício EnembreckPublished in: ICCS (2016)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- function approximation
- dynamic programming
- reinforcement learning algorithms
- genetic algorithm
- multiple users
- optimal policy
- evolutionary algorithm
- multi agent
- learning process
- transfer learning
- search engine
- optimal control
- learning algorithm
- databases
- policy iteration