Deep Reinforcement Learning for System-on-Chip: Myths and Realities.
Tegg Tae Kyong SungBo RyuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- hardware and software
- function approximation
- reinforcement learning algorithms
- power consumption
- markov decision processes
- embedded systems
- state space
- model free
- optimal control
- dynamic programming
- learning problems
- temporal difference learning
- direct policy search
- design methodology
- learning capabilities
- action space
- robotic control
- transfer learning
- mobile robot
- multi agent
- decision making
- learning algorithm
- supervised learning
- action selection
- search space
- control problems
- markov decision process
- deep learning
- multi agent reinforcement learning
- relational reinforcement learning
- machine learning
- real time