Stabilizing Off-Policy Deep Reinforcement Learning from Pixels.
Edoardo CetinPhilip J. BallStephen J. RobertsOya ÇeliktutanPublished in: ICML (2022)
Keyphrases
- reinforcement learning
- function approximation
- input image
- model free
- reinforcement learning algorithms
- state space
- markov decision processes
- pixel wise
- reinforcement learning methods
- pixel classification
- optimal policy
- data sets
- optimal control
- image pixels
- pixel values
- multi agent
- least squares
- nonlinear systems
- homogeneous regions
- deep learning
- learning algorithm
- machine learning