GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning.
Jiajun FanChangnan XiaoYue HuangPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- supervised learning
- temporal difference
- learning problems
- learning algorithm
- machine learning
- function approximation
- state space
- kernel based learning
- unsupervised learning
- active learning
- semi supervised
- dynamic programming
- reinforcement learning algorithms
- learning tasks
- low power
- multi agent
- learning process
- training examples
- markov decision processes
- statistical learning
- model free
- action selection
- information systems
- training data
- training set
- optimal policy
- training samples