Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping by State Representation Learning Based on a Preprocessed Input Image.
Tae Won KimYeseong ParkYoungbin ParkSang Hyoung LeeIl Hong SuhPublished in: IROS (2021)
Keyphrases
- reinforcement learning
- actor critic
- input image
- state space
- policy gradient
- learning process
- learning algorithm
- temporal difference
- reinforcement learning algorithms
- supervised learning
- learning problems
- learning tasks
- function approximation
- optimal control
- neuro fuzzy
- reinforcement learning methods
- machine learning algorithms
- approximate dynamic programming
- action selection
- saliency map
- markov decision processes
- skin color
- partially observable
- markov decision process
- policy iteration
- temporal difference learning
- dynamic programming