Distributed Deep Reinforcement Learning: Learn How to Play Atari Games in 21 minutes.
Igor AdamskiRobert AdamskiTomasz GrelAdam JedrychKamil KaczmarekHenryk MichalewskiPublished in: ISC (2018)
Keyphrases
- reinforcement learning
- reinforcement learning agents
- game playing
- linear value function approximation
- multi agent
- game players
- function approximation
- function approximators
- cooperative
- video games
- state space
- temporal difference learning
- model free
- markov decision processes
- learning algorithm
- imperfect information
- action selection
- machine learning
- game theory
- learning agent
- search space
- reinforcement learning methods
- multi agent systems
- games played
- optimal policy