set up rl-human-prefs

rl-human-prefs/.flake8

@@ -0,0 +1,4 @@
+[flake8]
+ignore = E203, W503
+max-line-length = 119
+

rl-human-prefs/.gitignore

@@ -0,0 +1,14 @@
+# python
+__pycache__/
+
+# mypy
+/.mypy_cache
+
+# tox
+/.tox
+
+# pyenv
+.python-version
+
+# poetry
+/dist

rl-human-prefs/.isort.cfg

@@ -0,0 +1,3 @@
+[settings]
+profile = black
+

rl-human-prefs/mypy.ini

@@ -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
+

rl-human-prefs/pyproject.toml

@@ -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"

rl-human-prefs/src/rl_human_prefs/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

rl-human-prefs/tests/test_rl_human_prefs.py

@@ -0,0 +1,5 @@
+from rl_human_prefs import __version__
+
+
+def test_version() -> None:
+    assert __version__ == "0.1.0"

rl-human-prefs/tox.ini

@@ -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 .