# Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning

arXiv: https://arxiv.org/abs/1903.08543 · HTML: https://mlsanity.com/paper/1903.08543/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2019.

## Built on by (most cited first, 3 of 3)

- [Decoding complexity: how machine learning is redefining scientific discovery](https://mlsanity.com/paper/2405.04161/) (2024)
- [Dynamic programming with incomplete information to overcome navigational uncertainty in a nautical environment](https://mlsanity.com/paper/2112.14657/) (2021)
- [Estimating Reaction Barriers with Deep Reinforcement Learning](https://mlsanity.com/paper/2407.12453/) (2024)

## Abstract (arXiv)

Using a model heat engine, we show that neural network-based reinforcement learning can identify thermodynamic trajectories of maximal efficiency. We consider both gradient and gradient-free reinforcement learning. We use an evolutionary learning algorithm to evolve a population of neural networks, subject to a directive to maximize the efficiency of a trajectory composed of a set of elementary thermodynamic processes; the resulting networks learn to carry out the maximally-efficient Carnot, Stirling, or Otto cycles. When given an additional irreversible process, this evolutionary scheme learns a previously unknown thermodynamic cycle. Gradient-based reinforcement learning is able to learn the Stirling cycle, whereas an evolutionary approach achieves the optimal Carnot cycle. Our results show how the reinforcement learning strategies developed for game playing can be applied to solve physical problems conditioned upon path-extensive order parameters.