Fix PPO log_ratio bug (#509) #1058

	name: Build

	on:
	push:
	branches: [ main ]
	pull_request:
	branches: [ main ]

	jobs:
	build:

	runs-on: ubuntu-latest

	steps:
	- uses: actions/checkout@v2

	- name: Set up Python 3.8
	uses: actions/setup-python@v2
	with:
	python-version: 3.8
	cache: 'pip'

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install -r requirements.txt
	# Install extras
	# [bnb] (TODO: Remove `scipy` once `bnb` adds it as hard dep)
	pip install bitsandbytes scipy
	# [dev]
	pip install black hypothesis isort flake8 pre-commit pytest pytest-cov

	- name: Lint with flake8
	run: \|
	# Stop the build if there are Python syntax errors or undefined names
	flake8 . --count --select=E9,F63,F7 --show-source --statistics
	# Exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
	flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics

	- name: Run tests
	run: \|
	pytest -vv --cov=trlx/ tests/

	- name: Upload coverage to Codecov
	run: \|
	bash <(curl -s https://codecov.io/bash) -t $CODECOV_TOKEN

Provide feedback