Device Codesign using Reinforcement Learning.
Suma George CardwellKaran PatelCatherine D. SchumanJ. Darby SmithJaesuk KwonAndrew MaickeJared ArzateJean Anne C. IncorviaPublished in: ISCAS (2024)
Keyphrases
- reinforcement learning
- function approximation
- robotic control
- hardware software
- machine learning
- learning algorithm
- state space
- multi agent reinforcement learning
- learning process
- optimal policy
- markov decision processes
- model free
- learning problems
- mobile terminals
- reinforcement learning algorithms
- neural network
- temporal difference
- transfer learning
- low cost
- reinforcement learning methods
- stochastic approximation
- dynamic programming
- multi agent
- policy search
- portable devices
- real world