Unlocking Pixels for Reinforcement Learning via Implicit Attention.
Krzysztof ChoromanskiDeepali JainJack Parker-HolderXingyou SongValerii LikhosherstovAnirban SantaraAldo PacchianoYunhao TangAdrian WellerPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- input image
- image processing
- autonomous mental development
- multi agent
- state space
- markov decision processes
- spatial correlation
- focus of attention
- temporal difference
- pixel values
- visual attention
- data sets
- multiscale
- machine learning
- neural network
- image quality
- learning process
- multi agent systems
- image pixels
- model free
- learning algorithm
- reinforcement learning algorithms
- pixel classification
- autonomous learning
- multi agent reinforcement learning