Learning Open-Loop Saccadic Control of a 3D Biomimetic Eye Using the Actor-Critic Algorithm.
Henrique GranadoReza Javanmard AlitappehAkhil JohnA. John van OpstalAlexandre BernardinoPublished in: IROS (2023)
Keyphrases
- actor critic
- learning algorithm
- open loop
- cost function
- optimal control
- reinforcement learning
- policy gradient
- feedback control
- computational complexity
- control system
- objective function
- closed loop
- dynamic programming
- gradient method
- learning problems
- neuro fuzzy
- learning tasks
- temporal difference
- inverted pendulum
- np hard
- optimal solution
- machine learning