27 lines
785 B
Python
27 lines
785 B
Python
|
"""HPI: Homotopy-Based Policy Iteration for Adaptive Optimal Control.
|
||
|
|
|
||
|
|
Implements the algorithm from:
|
||
|
|
Chen et al., "Adaptive Optimal Control of Unknown Nonlinear Systems
|
||
|
|
via Homotopy-Based Policy Iteration", IEEE TAC, 2024.
|
||
|
|
|
||
|
|
Uses neural network function approximators (CriticNN, ActorNN) trained
|
||
|
|
via gradient-based Bellman residual minimization.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from .nn_models import (ActorNN, CriticNN, check_lyapunov_decrease,
|
||
|
|
check_positive_definite, compute_q)
|
||
|
|
from .data_collector import DataCollector
|
||
|
|
from .nn_trainer import NNTrainer
|
||
|
|
from .hpi_controller import HPIController
|
||
|
|
|
||
|
|
__all__ = [
|
||
|
|
"CriticNN",
|
||
|
|
"ActorNN",
|
||
|
|
"compute_q",
|
||
|
|
"check_positive_definite",
|
||
|
|
"check_lyapunov_decrease",
|
||
|
|
"DataCollector",
|
||
|
|
"NNTrainer",
|
||
|
|
"HPIController",
|
||
|
|
]
|