Alexey Skrynnik

It seems like you are trying to run an example from version [pogema 1.0.1](https://pypi.org/project/pogema/1.0.1/), but you have installed pogema 1.2.2. Note that version 1.2.2 does not use "gym"; instead, it...

Could you specify the versions of the libraries you are using? I don’t have a machine with Windows, but I'll attempt to reproduce your error on Linux. How did you...

Based on what I can see, you are using versions that are different from those specified in docker/requirements.txt. I recommend trying with those specific versions. Additionally, I have been unable...

I haven’t experienced this specific issue. However, it might be related to insufficient RAM, especially if the problem does not occur with simpler configurations. I recommend monitoring your system’s memory...

Indeed, the PyMARL code is a bit outdated. In my opinion, it might not be worthwhile to delve deeply into identifying the specific error, as it's likely attributable to outdated...

> New ISSUE: Hi, I was wondering how much memory do you actually need to run 32x32 and 64x64 experiments? I've tested it on a server with 256GB of RAM.

Hi and thank you for your interest! The Baselines repository will not be receiving any future updates. The main baselines have been transferred to the [POGEMA-Benchmark](https://github.com/Cognitive-AI-Systems/pogema-benchmark) repository, which includes more...

First, I have observed this error with certain versions of gymnasium. Could you please share the versions of pogema, pogema-toolbox, and gymnasium you are using (from the output of pip...

If you want to change the `map_name`, you can directly modify it in yaml file. We can replace `map_name: wfi_warehouse` to any available map_name, which can be found in this...

Let’s take this ablation experiment as an example. When you run `eval.py` for the warehouse experiment, there are three types of Follower algorithms: `Follower`, `No dynamic cost`, and `No static...