Train Example #1

	name: Train Example
	on:
	workflow_dispatch:
	push:
	paths:
	- '**.py'
	pull_request:
	paths:
	- '**.py'

	jobs:
	train-example:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: '3.9'
	cache: 'pip'
	- name: Install dependencies
	run: \|
	pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
	pip install -e .
	- name: Train agent and check result
	run: \|
	python src/main.py --model=dqn --hidden-dim=8 --random-topology=1 --mini-batch-size=32 --device=cpu --episode-steps=1 --eval-episode-steps=1 --lr=0.001 --tau=0.01 --netmon --netmon-encoder-dim=4 --hidden-dim=4 --netmon-dim=2 --netmon-iterations=1 --sequence-length=1 --step-before-train=1_000 --capacity=10_000 --eval-episodes=100 --total-steps=5_000 --env-type=simple --epsilon=0.1 --epsilon-decay=1.0 --seed=0 --disable-progress \| tee -a train.txt
	cat train.txt \| grep "\"reward_mean\": 1.0"

Provide feedback