Learning to Maximize Return in a Stag Hunt Collaborative Scenario through Deep Reinforcement Learning.
Andrei Cristian NicaTudor BerariuFlorin GogianuAdina Magda FloreaPublished in: SYNASC (2017)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning problems
- supervised learning
- active learning
- learning systems
- real world
- function approximation
- learning tasks
- knowledge acquisition
- online learning
- mobile learning
- dynamic programming
- prior knowledge
- neural network
- problem based learning
- learning agents
- temporal difference learning
- evolutionary learning