Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Factorio Learning Environment – Agents Build Factories

jackhopkins.github.io

Post reply on HN
Print view View original

101–110 of 225 posts

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#101

Post by noddybear »

barrystaes wrote: post #79

I have long dreamt of automating Factorio in the way that HDL and a PCB router works: just specify the ingredients and it produces a Factorio Blueprint. First MVP stupid designs, then optimized routing, and eventually usable ingame where it connects with provided in/outputs. Would be more fun to develop than to play obviously.. I liked the nilhouse mega base with that factory-train-blocks blueprints, its basically Fa…

Someone created this Terraform provider for Factorio a few years ago: https://registry.terraform.io/providers/efokschaner/factorio...

I think this could be a good starting point for what you describe! This stuff is always more fun to develop than play. Since started working on this project, I can't bring myself to play the core game myself...

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#102

Post by noddybear »

vessenes wrote: post #90
noddybear wrote: post #78

Earlier quoted context omitted.

I think your intuition is correct about the amount of information that needs to be encoded into an ASCII char. You could potentially use unicode to pack more more into each char, e.g direction, type, status etc. Or make each representation available on-demand, i.e 'show me the direction of all inserters in a 10 tile radius'.

Well we learned last month on HN that you can encode arbitrary data into Unicode; anecdotally, o3-mini-high at least could decode it if given instructions. I wonder what a quick way to calculate how many Unicode characters you’d need is.. I guess every entity + four orientations. Underground belts and pipes seem tough. But I guess you could just add an encoding showing if the square has an underground pipe or encodin…

Checkout the 'ObserveAll' tool in the repo - its deprecated now, but it pipes all the raw entities on the map back to the agent. You could procedurally convert it to unicode format given a pre-defined codebook (which you give to the agent) before letting the agent observe and reason over it.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#103

Post by delichon »

barrystaes wrote: post #79

I have long dreamt of automating Factorio in the way that HDL and a PCB router works: just specify the ingredients and it produces a Factorio Blueprint. First MVP stupid designs, then optimized routing, and eventually usable ingame where it connects with provided in/outputs. Would be more fun to develop than to play obviously.. I liked the nilhouse mega base with that factory-train-blocks blueprints, its basically Fa…

I've wondered if automating Factorio would free me of the compulsion to play it.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#104

Post by infogulch »

eterm wrote: post #52
WJW wrote: post #27

Very cool and also pretty expected results tbh. Some thoughts: Factorio is a game that requires SIGNIFICANT amounts of thinking ahead, often requiring investments into things that won't pay off until much later and which might even significantly hamper initial development. Building a main bus vs spaghetti belts is one of the obvious examples here. Humans with a little bit of experience playing factorio know that whil…

> Building a main bus vs spaghetti belts is one of the obvious examples here I'm an anti-bus extremist. ( I've even considered regsitering BanTheBus.com and doing an over-the-top static anti-bus website. ), so take what I'm about to say with a pinch of salt. Also note that my post applies to non-space-age. Space-age changes the gameplay fundamentally, so this really only applies to factorio 1.1 or 2.0 with space-age…

I agree with everything you said, but I'd like to defend the main bus as a learning phase.

The main bus is for production capacity discovery. New players have to discover the production tree somehow and browsing recipe cards with a calculator before starting is not the way, it has to be hands-on and interactive. Dividing up your factory into (arbitrarily defined) intermediates production and final product production is helpful to cut through the complexity. Of course, intermediate production will be severely underbuilt and logistics capacity will never keep up with consumption of all of the final product builds, but it will be enough to run a couple builds at once and test new ones.

Once new players have a grasp of the scope of the production tree, with tangible examples of sub-factories, then they can begin to consider end-to-end production capacity.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#105

Post by robotresearcher »

noddybear wrote: post #68
spieswl wrote: post #62

Fantastic idea. It seems like there are a lot of interesting experiments to be had here. The lab-play scenarios having a time-related component seems like a good idea, I assume most Factorio players that keep biters on treat them as a combined temporal-spatial constraint, so you have a sort-of proxy comparison to a real game situation when you put the agents on a timer. I like the way that the framework design is tes…

One thing we've been talking about is creating tasks that are a bit more 'tower defence', where biters are released every X steps / seconds. The idea would be to test agents in building a military-industrial complex. One amusing issue we had in developing this idea is that frontier models have an aversion to creating entities called 'GunTurret' etc - as it goes against their constitution! (perhaps we should rename tu…

If (1) is a special case of (2), maybe you’d only need (2)?

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#106

Post by sdwr »

eterm wrote: post #52
WJW wrote: post #27

Very cool and also pretty expected results tbh. Some thoughts: Factorio is a game that requires SIGNIFICANT amounts of thinking ahead, often requiring investments into things that won't pay off until much later and which might even significantly hamper initial development. Building a main bus vs spaghetti belts is one of the obvious examples here. Humans with a little bit of experience playing factorio know that whil…

> Building a main bus vs spaghetti belts is one of the obvious examples here I'm an anti-bus extremist. ( I've even considered regsitering BanTheBus.com and doing an over-the-top static anti-bus website. ), so take what I'm about to say with a pinch of salt. Also note that my post applies to non-space-age. Space-age changes the gameplay fundamentally, so this really only applies to factorio 1.1 or 2.0 with space-age…

The most challenging part of factorio is routing inputs and outputs in 2D. If you build naively, intersections between ingredient belts choke the life out of your factory (3 utilities problem). Bus guarantees building space with easy access to all ingredients.

Sure, if you already know what you're doing, you can plan ahead and leave space for the right things. For everyone else, it simplifies the game to a manageable level.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#107

Post by noddybear »

delichon wrote: post #103
barrystaes wrote: post #79

I have long dreamt of automating Factorio in the way that HDL and a PCB router works: just specify the ingredients and it produces a Factorio Blueprint. First MVP stupid designs, then optimized routing, and eventually usable ingame where it connects with provided in/outputs. Would be more fun to develop than to play obviously.. I liked the nilhouse mega base with that factory-train-blocks blueprints, its basically Fa…

I've wondered if automating Factorio would free me of the compulsion to play it.

It certainly did with me.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#108

Post by jillyboel »

vessenes wrote: post #84

OK, You’ve permanently nerd-baited me, and I wish to apply for a job at the Anthropic Factorio lab immediately. I can’t tell from the paper or these comments if you’re sending multimodal data back — I’m guessing no, because many of these models aren’t multimodal. But some are — and of course we now have recently released Qwen 2.5 VLM which seems to be quite strong for its size. You harp on this lack of spatial abilit…

Why would screenshots be necessary if a textual description of the factory state is both easier to interpret and less prone to confusion? The game is played on a grid, so converting the game state to ascii ought to be trivial.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#109

Post by vessenes »

martbakler wrote: post #92
vessenes wrote: post #84

OK, You’ve permanently nerd-baited me, and I wish to apply for a job at the Anthropic Factorio lab immediately. I can’t tell from the paper or these comments if you’re sending multimodal data back — I’m guessing no, because many of these models aren’t multimodal. But some are — and of course we now have recently released Qwen 2.5 VLM which seems to be quite strong for its size. You harp on this lack of spatial abilit…

Currently it's a text-only modality environment but we are planning to support vision in the future. We did run a couple of tests and saw that including screenshots of the game state did not improve performance on the off-the-shelf models. As the complexity of the game state grew and the screenshots were filled with more entities, the models got even more confused and started hallucinating directions, entities etc or…

That makes sense and it’s really interesting - it is a challenging visual test for sure; thousands of entities, either multi tier visual representations (screen, map, overview map) or a GIANT high res image. I hereby propose FLE-V a subset benchmark for visual models where they just turn a factorio image into a proper FLE description. And maybe the overview and map images as well.

Re: Show HN: Factorio Learning Environment – Agents Build Factories

#110

Post by vessenes »

jillyboel wrote: post #108
vessenes wrote: post #84

OK, You’ve permanently nerd-baited me, and I wish to apply for a job at the Anthropic Factorio lab immediately. I can’t tell from the paper or these comments if you’re sending multimodal data back — I’m guessing no, because many of these models aren’t multimodal. But some are — and of course we now have recently released Qwen 2.5 VLM which seems to be quite strong for its size. You harp on this lack of spatial abilit…

Why would screenshots be necessary if a textual description of the factory state is both easier to interpret and less prone to confusion? The game is played on a grid, so converting the game state to ascii ought to be trivial.

Trivial as in only engineering work, sure. But it’s a lottt of tokens. Long context models do a number of things to get all that working context in; some of those things elide details / compress / have token segments that are harder to reason about. When a burner inserter at a location takes up like 50-100 tokens, and you want it to reason about 100 of them, this is still a pretty challenging task for any LLM.
Post reply on HN