Neel Kant

You can only really hope to express things in vectorized form if you know a prior the maximum number of entities. In data 2 there are 5 champions per side...

the render tool does have some annotations which are super helpful for a zero-shot agent. See the side-by-side images in the "Vision Agents" section of https://jackhopkins.github.io/factorio-learning-environment/0.2.0.html . With vision fine-tuning...

Yes, we should use the new renderer. We just need to figure out what the center and zoom level should be to line up with the player's view when they...

yes that would be ideal for sure. To my knowledge no one on the team has attempted to convert the client binary into a headless server and try to use...

The score() function is called just as a check with instance is initialized (instance.py:123).I had seen this error earlier where the score tool returned an empty dictionary while the expected...

We could un-silence the mod-loading, but they get loaded so quickly and the game console chat doesn't allow scrolling so I don't know if that's the best approach for debugging....

The gym observation space was meant to capture whatever was being used in the original environment and trajectory runner loop. In this case the info is coming from `ThroughputTask.verify() ->...

I think you're right there's something not right here. The fact that `eval_program_with_achievements()` calls `self.instance.eval_with_error` seems off.

Not sure if that's enough to be really helpful since there's placement but also configuration (rotation, recipe-setting). I think we just need to look at the event trace from @hrshtt...

I like the increased modularity and separation of concerns in the instance and session levels. I also like the additional structure with new classes like `AbstractTrajectoryRunner`, `GameConfig`, `FactorioClient`, `ToolHookRegistry` etc....