Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes.
Igor AdamskiRobert AdamskiTomasz GrelAdam JedrychKamil KaczmarekHenryk MichalewskiPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- game playing
- reinforcement learning agents
- linear value function approximation
- multi agent
- imperfect information
- game theory
- temporal difference learning
- cooperative
- dynamic programming
- games played
- game players
- computer games
- function approximators
- learning agent
- game theoretic
- machine learning
- nash equilibrium
- function approximation
- supervised learning
- state space
- temporal difference
- learning capabilities
- control problems
- multi agent systems
- video games
- transfer learning
- learning process