DTRL: Decision Tree-based Multi-Objective Reinforcement Learning for Runtime Task Scheduling in Domain-Specific System-on-Chips.
Toygun BasaklarA. Alper GoksoyAnish KrishnakumarSuat GumussoyÜmit Y. OgrasPublished in: ACM Trans. Embed. Comput. Syst. (2023)
Keyphrases
- multi objective
- domain specific
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- domain independent
- function approximation
- general purpose
- scheduling algorithm
- high speed
- genetic algorithm
- multiobjective optimization
- multi objective optimization problems
- conflicting objectives
- particle swarm optimization
- multiple objectives
- objective function
- reinforcement learning algorithms
- state space
- machine learning
- optimization problems
- learning algorithm
- optimal policy
- transactional memory
- high end
- nsga ii
- multi objective evolutionary
- pareto optimal
- bi objective
- computing systems
- temporal difference
- action selection
- model free
- massively parallel
- computing environments
- multi agent
- trade off
- domain experts
- computer systems
- integrated circuit
- routing protocol
- energy aware
- dynamic programming
- multiagent evolutionary algorithm