Learning the Heater From Its Own Logs

Описание и применение

Автор заменил вручную заданную модель нагревателя на обученную модель, используя 4 800 записей переходов из симуляции, что привело к более точным предсказаниям температуры.

Задача

A hand‑written world‑model for a heater used arbitrary constants and was inaccurate for a real room. The model needed to learn the true dynamics from logged data.

Результат

The trained model outperformed the hand‑coded model, predicting room temperatures more accurately on unseen data.

Рабочий процесс

• Define realRoom function with true constants and noise.
• Generate 80 episodes of 60 steps each, recording state, action, and nextState.
• Use a thermostat to decide actions, injecting random actions every fifth step.
• Collect the log of Transition objects.
• Train a new predictive model on the logged data.
• Evaluate the trained model against unseen room states.
• Run the complete system in the browser.

Доказательства

The model is four numbers. The training loop is twenty lines.

Источник

Eight episodes gives 4,800 transitions, each one the Transition type from the 101 post.

Источник

The rule for the rest of the post is that nothing below this line gets to look inside realRoom.

Источник