←back to thread

Show HN: Factorio Learning Environment – Agents Build Factories

(jackhopkins.github.io)
749 points noddybear | 1 comments | 11 Mar 25 12:02 UTC | HN request time: 0.21s | source

I'm Jack, and I'm excited to share a project that has channeled my Factorio addiction recently: the Factorio Learning Environment (FLE).

FLE is an open-source framework for developing and evaluating LLM agents in Factorio. It provides a controlled environment where AI models can attempt complex automation, resource management, and optimisation tasks in a grounded world with meaningful constraints.

A critical advantage of Factorio as a benchmark is its unbounded nature. Unlike many evals that are quickly saturated by newer models, Factorio's geometric complexity scaling means it won't be "solved" in the next 6 months (or possibly even years). This allows us to meaningfully compare models by the order-of-magnitude of resources they can produce - creating a benchmark with longevity.

The project began 18 months ago after years of playing Factorio, recognising its potential as an AI research testbed. A few months ago, our team (myself, Akbir, and Mart) came together to create a benchmark that tests agent capabilities in spatial reasoning and long-term planning.

Two technical innovations drove this project forward: First, we discovered that piping Lua into the Factorio console over TCP enables running (almost) arbitrary code without directly modding the game. Second, we developed a first-class Python API that wraps these Lua programs to provide a clean, type-hinted interface for AI agents to interact with Factorio through familiar programming paradigms.

Agents interact with FLE through a REPL pattern: 1. They observe the world (seeing the output of their last action) 2. Generate Python code to perform their next action 3. Receive detailed feedback (including exceptions and stdout)

We provide two main evaluation settings: - Lab-play: 24 structured tasks with fixed resources - Open-play: An unbounded task of building the largest possible factory on a procedurally generated map

We found that while LLMs show promising short-horizon skills, they struggle with spatial reasoning in constrained environments. They can discover basic automation strategies (like electric-powered drilling) but fail to achieve more complex automation (like electronic circuit manufacturing). Claude Sonnet 3.5 is currently the best model (by a significant margin).

The code is available at https://github.com/JackHopkins/factorio-learning-environment.

You'll need: - Factorio (version 1.1.110) - Docker - Python 3.10+

The README contains detailed installation instructions and examples of how to run evaluations with different LLM agents.

We would love to hear your thoughts and see what others can do with this framework!

Show context
iliketrains ◴[11 Mar 25 16:33 UTC] No.43334194[source]▶
This is awesome! I like the idea of abstracting the factory building with a code-like structure. I wonder if supplemental 2D image (mini-map style) as an input to the policy would help with the spatial reasoning?

I work on a similar factory game (Captain of Industry) and I have always wanted an agent that can play the game for testing and balancing reasons. However, pixels-to-mouse-actions RL policy (similar to Deep Mind's StarCraft agent) always seemed like a very hard and inefficient approach. Using code-like API seems so much better! I might try to find some time to port this framework to COI :) Thanks for sharing!

replies(2): >>43334413 #>>43334470 #
noddybear ◴[11 Mar 25 16:52 UTC] No.43334470[source]▶
Regarding the 2d image - the issue is that these frontier models don't tend to support supplemental image inputs, and the ones that do aren't sufficiently well trained on (high precision) Factorio visuals to add that much information.
replies(1): >>43335458 #
iliketrains ◴[11 Mar 25 18:18 UTC] No.43335458[source]▶
I see, integrating image inputs can be very challenging in this case as the models work with text input. I was not even thinking about the full isometric image, but just some simple 2D map where each pixel can be color-coded based on the entity type. I guess the problem is that these maps would look like nothing the models were trained on, so as you say, it might not provide any value.

The reason I was suggesting this is that I worked in robotics making RL policies, and supplying image data (be it maps, lidar scans, etc.) was a common practice. But our networks were custom made to ingest these data and trained from scratch, which is quite different from this approach.

replies(1): >>43337219 #
1. martbakler ◴[11 Mar 25 21:30 UTC] No.43337219[source]▶
Indeed I think the trade-off here is the more "pure factorio" types of images we give to the agents, the more likely it is that they've seen it during training (from google etc), however the signal-to-noise ratio is low and hence the current models get confused as the map complexity (amount of entities) and level of detail grows. If we start to create custom images, we can reduce the unneeded noise, but then risk giving something completely OOD to the agent (unless we train a visual encoder) and the performance also tanks