PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning.
Rajarshi RoyJonathan RaimanNeel KantIlyas ElkinRobert KirbyMichael Y. SiuStuart F. ObermanSaad GodilBryan CatanzaroPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimization problems
- data structure
- optimization algorithm
- parallel implementation
- global optimization
- optimization process
- machine learning
- constrained optimization
- parallel processing
- multi agent
- parallel computing
- optimization methods
- function approximation
- learning algorithm
- distributed memory
- combinatorial optimization
- transfer learning
- high speed
- model free
- action selection
- supervised learning
- bit parallel