Spectrum Random Masking for Generalization in Image-based Reinforcement Learning.
Yangru HuangPeixi PengYifan ZhaoGuangyao ChenYonghong TianPublished in: NeurIPS (2022)
Keyphrases
- action selection
- reinforcement learning
- temporal difference
- function approximation
- policy search
- uniformly distributed
- machine learning
- computer vision
- multi agent
- state space
- transfer learning
- human visual system
- model free
- markov decision processes
- function approximators
- reinforcement learning algorithms
- optimal control
- data sets
- dynamic programming
- multiresolution
- neural network