Optimizing Memory Mapping Using Deep Reinforcement Learning.
Pengming WangMikita SazanovichBerkin IlbeyiPhitchaya Mangpo PhothilimthanaManish PurohitHan Yang TayNgân VuMiaosen WangCosmin PaduraruEdouard LeurentAnton ZhernovJulian SchrittwieserThomas HubertRobert TungPaula KurylowiczKieran MilanOriol VinyalsDaniel J. MankowitzPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- memory usage
- reinforcement learning algorithms
- memory space
- learning algorithm
- information retrieval
- temporal difference learning
- optimal policy
- memory requirements
- markov decision processes
- random access
- computing power
- transfer learning
- case study
- reinforcement learning methods
- data sets
- temporal difference
- main memory
- hidden markov models
- multi agent
- information systems
- machine learning