Deep Reinforcement Learning amidst Continual Structured Non-Stationarity.
Annie XieJames HarrisonChelsea FinnPublished in: ICML (2021)
Keyphrases
- reinforcement learning
- non stationary
- function approximation
- temporal difference
- structured data
- markov decision processes
- reinforcement learning algorithms
- model free
- real world
- temporal difference learning
- state space
- optimal policy
- autonomous learning
- databases
- structured learning
- markov decision process
- evaluation function
- dynamical systems
- unsupervised learning
- learning process
- decision making
- learning algorithm
- data mining
- neural network