Model-free forecasting of partially observable spatiotemporally chaotic systems.
Vikrant GuptaLarry K. B. LiShiyi ChenMinping WanPublished in: Neural Networks (2023)
Keyphrases
- model free
- partially observable
- reinforcement learning
- chaotic systems
- adaptive control
- initial conditions
- state space
- reinforcement learning algorithms
- function approximation
- markov decision processes
- markov decision problems
- temporal difference
- decision problems
- policy iteration
- learning algorithm
- control method
- dynamical systems
- reward function
- control parameters
- infinite horizon
- multi agent
- partially observable markov decision processes
- control scheme
- supervised learning
- belief state
- machine learning
- data mining
- closed loop