A Scalable and Reproducible System-on-Chip Simulation for Reinforcement Learning.
Tegg Tae Kyong SungBo RyuPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- hardware and software
- simulation model
- simulation study
- function approximation
- neural network
- simulation models
- low cost
- dynamic programming
- multi agent
- learning algorithm
- least squares
- mathematical model
- transfer learning
- hidden markov models
- embedded systems
- optimal control
- simulation environment
- reinforcement learning algorithms
- web scale
- database
- real robot
- design space exploration