Al momento, stai seguendo questo contributo
- Vedrai gli aggiornamenti nel tuo feed del contenuto seguito
- Potresti ricevere delle email a seconda delle tue preferenze per le comunicazioni
This fileexchange provides a clean, modular implementation of the Proximal Policy Optimization (PPO) algorithm with clipping (PPO‑Clip) using MATLAB® and the Deep Learning Toolbox™. It is tailored for continuous action spaces and can be easily adapted to any custom environment by simply replacing the environment functions.
The core algorithm is built entirely with dlnetwork objects, enabling automatic differentiation, GPU acceleration, and full compatibility with custom training loops.
Cita come
Chuguang Pan (2026). PPO Deep Reinforcement Learning Control Example (https://it.mathworks.com/matlabcentral/fileexchange/183907-ppo-deep-reinforcement-learning-control-example), MATLAB Central File Exchange. Recuperato .
Informazioni generali
- Versione 1.0.1 (9,25 KB)
Compatibilità della release di MATLAB
- Compatibile con qualsiasi release
Compatibilità della piattaforma
- Windows
- macOS
- Linux
