Deep Reinforcement Learning amidst Lifelong Non-Stationarity.
Annie XieJames HarrisonChelsea FinnPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- non stationary
- function approximation
- reinforcement learning algorithms
- state space
- markov decision processes
- learning algorithm
- model free
- st century
- supervised learning
- policy search
- temporal difference
- learning scenarios
- learning problems
- dynamic programming
- learning process
- data mining
- robotic control
- competence development
- belief nets
- temporal difference learning
- action space
- database
- lifelong learning
- action selection
- learning activities
- genetic algorithm
- real world
- data sets