Deep Q-Learning with Prioritized Sampling.
Jianwei ZhaiQuan LiuZongzhang ZhangShan ZhongHaijun ZhuPeng ZhangCijia SunPublished in: ICONIP (1) (2016)
Keyphrases
- reinforcement learning
- cooperative
- multi agent
- state space
- function approximation
- model free
- random sampling
- learning algorithm
- sampling algorithm
- stochastic approximation
- learning rate
- sampling methods
- feature space
- monte carlo
- temporal difference learning
- sampling strategy
- sampled data
- possibilistic logic
- sampling strategies
- parameter space
- action selection
- data sets
- image reconstruction
- active learning
- genetic algorithm
- machine learning
- neural network