SLER: Self-generated long-term experience replay for continual reinforcement learning.
Chunmao LiYang LiYinliang ZhaoPeng PengXupeng GengPublished in: Appl. Intell. (2021)
Keyphrases
- long term
- reinforcement learning
- short term
- model free
- learning algorithm
- function approximation
- markov decision processes
- action selection
- temporal difference
- state space
- supervised learning
- optimal policy
- digital libraries
- user experience
- search algorithm
- databases
- reinforcement learning algorithms
- temporal difference learning