Skip to content

Commit

Permalink
Merge pull request #9 from yamatokataoka/set-up-rl-human-prefs
Browse files Browse the repository at this point in the history
set up rl-human-prefs
  • Loading branch information
yamatokataoka authored Jan 29, 2022
2 parents 5f06934 + 55adc12 commit e64498e
Show file tree
Hide file tree
Showing 11 changed files with 342 additions and 0 deletions.
4 changes: 4 additions & 0 deletions rl-human-prefs/.flake8
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
[flake8]
ignore = E203, W503
max-line-length = 119

14 changes: 14 additions & 0 deletions rl-human-prefs/.gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
# python
__pycache__/

# mypy
/.mypy_cache

# tox
/.tox

# pyenv
.python-version

# poetry
/dist
3 changes: 3 additions & 0 deletions rl-human-prefs/.isort.cfg
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
[settings]
profile = black

Empty file added rl-human-prefs/README.md
Empty file.
12 changes: 12 additions & 0 deletions rl-human-prefs/mypy.ini
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
[mypy]
ignore_missing_imports = True
disallow_untyped_calls = True
disallow_untyped_defs = True
disallow_incomplete_defs = True
no_implicit_optional = True
warn_redundant_casts = True
warn_unused_ignores = True
warn_return_any = True
warn_unreachable = True
strict_equality = True

244 changes: 244 additions & 0 deletions rl-human-prefs/poetry.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

29 changes: 29 additions & 0 deletions rl-human-prefs/pyproject.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
[tool.poetry]
name = "rl-human-prefs"
version = "0.1.0"
description = "Replication of Deep Reinforcement Learning from Human Preferences (Christiano et al, 2017)."
license = "MIT"
authors = ["Yamato Kataoka"]
readme = "README.md"
homepage = "https://github.com/yamatokataoka/learning-from-human-preferences"
repository = "https://github.com/yamatokataoka/learning-from-human-preferences"
keywords = ["rl-human-prefs", "reinforcement learning", "deep learning", "pytorch", "AI safety"]
classifiers = [
"Development Status :: 4 - Beta",
"Intended Audience :: Developers",
"Intended Audience :: Education",
"Intended Audience :: Science/Research",
"Programming Language :: Python :: 3",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Software Development :: Libraries"
]

[tool.poetry.dependencies]
python = "^3.7"

[tool.poetry.dev-dependencies]
tox = "^3.24.5"

[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"
1 change: 1 addition & 0 deletions rl-human-prefs/src/rl_human_prefs/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
__version__ = "0.1.0"
Empty file.
5 changes: 5 additions & 0 deletions rl-human-prefs/tests/test_rl_human_prefs.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
from rl_human_prefs import __version__


def test_version() -> None:
assert __version__ == "0.1.0"
30 changes: 30 additions & 0 deletions rl-human-prefs/tox.ini
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
[tox]
envlist = py310, check, fix
isolated_build = true

[testenv]
deps = pytest
commands = pytest -rA tests

[testenv:check]
skip_install = true
deps =
isort
black
flake8
mypy
commands =
isort --diff .
black --diff .
flake8 .
mypy .


[testenv:fix]
skip_install = true
deps =
isort
black
commands =
isort .
black .

0 comments on commit e64498e

Please sign in to comment.