Research Article
A Direct Reinforcement Learning Approach for Nonautonomous Thermoacoustic Generator
| Step 1: Initialization: . | | Step 2: Solving the admissible control from optimization problem: | | | | With is a positive definite function. | | Step 3: Solving a positive definite value function from the admissible control in Step 2: | | | | With and . | | Step 4: If or then go to Step 2. Else, go to Step 5. | | Step 5: Obtaining the approximate optimal value function and optimal control . |
|