search

RoboEden / Luxai-s2-Baseline

11 stars 1 forks source link

Are any modifications needed for neurips stage? #3

Closed wonjun-dev closed 9 months ago

wonjun-dev commented 9 months ago

I followed README instructions, but i got a lot of assertion error on python train.py.

I modified map_size 48 to 64 and it resolves assertion error, but i faced value error:

File "/sources/Luxai-s2-Baseline/luxenv.py", line 329, in reset obs, rewards, dones, infos = self.proxy.step(actions) ValueError: too many values to unpack (expected 4)

Modification of 329th line of luxenv.py obs, rewards, dones, _, infos = self.proxy.step(actions) resloves the error, but it raised the other error

File "/opt/conda/envs/luxai_s2/lib/python3.8/site-packages/numpy/core/shape_base.py", line 471, in stack return _nx.concatenate(expanded_arrays, axis=axis, out=out, File "<__array_function__ internals>", line 200, in concatenate ValueError: Output array is the wrong shape

Schopenhauer-loves-Hegel commented 9 months ago

The map_size issue has been fixed today and you can access the code here for gymnasium version: https://github.com/RoboEden/Luxai-s2-Baseline/tree/main/Luxai-s2-Baseline4gymnasium.

wonjun-dev commented 9 months ago

Thanks for your supporting!