Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation.
Michelle PanMariah SchrumVivek MyersErdem BiyikAnca D. DraganPublished in: CoRR (2024)
Keyphrases
- actor critic
- model based reinforcement learning
- reinforcement learning
- markov decision processes
- policy iteration
- temporal difference
- policy gradient
- optimal control
- gradient method
- reinforcement learning algorithms
- approximate dynamic programming
- function approximation
- neuro fuzzy
- state space
- multi agent
- semi supervised learning