Image Classification by Reinforcement Learning with Two-State Q-Learning.
Abdul Mueed HafizGhulam Mohiuddin BhatPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- state space
- image classification
- function approximation
- reinforcement learning algorithms
- model free
- learning algorithm
- optimal policy
- state abstraction
- stochastic approximation
- temporal difference learning
- action space
- multi agent
- bag of words
- action selection
- markov decision processes
- state variables
- dynamic programming
- partially observable
- state action
- feature extraction
- learning problems
- control problems
- learning agent
- multiscale
- multi agent reinforcement learning
- computer vision