Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint Replay.
Ionel-Alexandru HosuTraian RebedeaPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- computer games
- game playing
- linear value function approximation
- human players
- game players
- playing games
- function approximation
- games played
- imperfect information
- temporal difference learning
- online game
- video games
- optimal control
- board game
- learning algorithm
- nash equilibria
- game play
- game theory
- multi agent
- reinforcement learning algorithms
- neural network
- nash equilibrium
- real valued
- dynamic programming
- learning process
- foreign language learners
- machine learning