Reinforcement Learning Guided by Double Replay Memory.
JiSeong HanKichun JoWontaek LimYongHak LeeKyoungmin KoEunseon SimJunsang ChoSunghwan KimPublished in: J. Sensors (2021)
Keyphrases
- reinforcement learning
- function approximation
- memory usage
- memory size
- memory space
- temporal difference
- learning algorithm
- model free
- main memory
- optimal policy
- state space
- markov decision processes
- action selection
- decision making
- temporal difference learning
- memory requirements
- supervised learning
- computational power
- dynamic programming
- multi agent
- random access
- limited memory
- neural network
- low memory
- robotic control