Competitive Reinforcement Learning in Atari Games.
Mark McKenziePeter LoxleyWilliam BillingsleySebastien WongPublished in: Australasian Conference on Artificial Intelligence (2017)
Keyphrases
- reinforcement learning
- linear value function approximation
- function approximation
- reinforcement learning algorithms
- state space
- nash equilibria
- game theory
- temporal difference
- control problems
- learning algorithm
- optimal policy
- markov decision processes
- supervised learning
- temporal difference learning
- dynamic programming
- multi agent
- linear programming
- learning experience
- machine learning
- game theoretic
- control strategies
- cooperative
- partially observable
- stochastic games