Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Maithra RaghuAlex IrpanJacob AndreasRobert KleinbergQuoc V. LeJon M. KleinbergPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- learning agents
- action sets
- function approximation
- learning algorithm
- state space
- dynamic programming
- game theory
- video games
- model free
- multi agent
- monte carlo tree search
- reinforcement learning agents
- optimal policy
- markov decision processes
- search algorithm
- game playing
- online game
- function approximators
- temporal difference learning
- machine learning
- robotic control