Physics-Informed Critic in an Actor-Critic Reinforcement Learning for Swimming in Turbulence.
Christopher KohLaurent PagnierMichael ChertkovPublished in: CoRR (2024)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- optimal control
- reinforcement learning algorithms
- approximate dynamic programming
- neuro fuzzy
- gradient method
- function approximation
- policy iteration
- learning algorithm
- model free
- state space
- markov decision processes
- natural actor critic
- optimal policy
- reinforcement learning problems
- control problems
- policy gradient methods
- reinforcement learning methods
- function approximators
- transfer learning
- action selection
- markov chain
- finite state
- linear programming
- linear program
- supervised learning
- step size
- machine learning
- learning problems
- belief revision
- evaluation function