One-shot, Offline and Production-Scalable PID Optimisation with Deep Reinforcement Learning

no code implementations • 25 Oct 2022 • Zacharaya Shabka, Michael Enrico, Nick Parsons, Georgios Zervas

Furthermore, once trained (which takes $\mathcal{O}(hours)$), the model generates actuator-unique PID parameters in a one-shot inference process that takes $\mathcal{O}(ms)$ in comparison to up to $\mathcal{O}(week)$ required for conventional tuning methods, therefore accomplishing these performance improvements whilst achieving up to a $10^6\times$ speed-up.

reinforcement-learning Reinforcement Learning (RL)