Reinforcement Learning Based Dynamic Selection of Auxiliary Objectives with Preserving of the Best Found Solution.
Irina PetrovaArina BuzdalovaPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- linear equations
- solution space
- control policy
- multiple objectives
- multi agent
- optimal solution
- search algorithm
- solution quality
- multi objective
- function approximation
- closed form
- linear programming
- state space
- learning algorithm
- lower bound
- decision trees
- website
- information systems
- search engine