Playing Atari with Deep Reinforcement Learning.
Volodymyr MnihKoray KavukcuogluDavid SilverAlex GravesIoannis AntonoglouDaan WierstraMartin A. RiedmillerPublished in: CoRR (2013)
Keyphrases
- reinforcement learning
- linear value function approximation
- reinforcement learning problems
- function approximation
- reinforcement learning algorithms
- state space
- model free
- transfer learning
- control problems
- learning algorithm
- markov decision processes
- optimal control
- supervised learning
- markov decision problems
- dynamic programming
- temporal difference
- markov decision process
- game playing
- optimal policy
- multi agent