# Learning Light Transport the Reinforced Way

arXiv: https://arxiv.org/abs/1701.07403 · HTML: https://mlsanity.com/paper/1701.07403/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jan 2017.

## Built on by (most cited first, 5 of 5)

- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Neural Radiosity](https://mlsanity.com/paper/2105.12319/) (2021)
- [Path Guiding Using Spatio-Directional Mixture Models](https://mlsanity.com/paper/2111.13094/) (2021)
- [Manifold Path Guiding for Importance Sampling Specular Chains](https://mlsanity.com/paper/2311.12818/) (2023)
- [Neural Path Guiding with Distribution Factorization](https://mlsanity.com/paper/2506.00839/) (2025)

## Abstract (arXiv)

We show that the equations of reinforcement learning and light transport simulation are related integral equations. Based on this correspondence, a scheme to learn importance while sampling path space is derived. The new approach is demonstrated in a consistent light transport simulation algorithm that uses reinforcement learning to progressively learn where light comes from. As using this information for importance sampling includes information about visibility, too, the number of light transport paths with zero contribution is dramatically reduced, resulting in much less noisy images within a fixed time budget.