Migrate to gymnasium maintaining python 3.8 compatibility

.circleci/config.yml

@@ -8,7 +8,7 @@ orbs:
 
 defaults: &defaults
   docker:
-    - image: humancompatibleai/seals:base
+    - image: humancompatibleai/seals:base-alpha
       auth:
         username: $DOCKERHUB_USERNAME
         password: $DOCKERHUB_PASSWORD

Dockerfile

@@ -1,6 +1,6 @@
 # base stage contains just binary dependencies.
 # This is used in the CI build.
-FROM nvidia/cuda:10.0-runtime-ubuntu18.04 AS base
+FROM nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu20.04 AS base
 ARG DEBIAN_FRONTEND=noninteractive
 
 RUN    apt-get update -q \
@@ -9,6 +9,7 @@ RUN    apt-get update -q \
     curl \
     ffmpeg \
     git \
+    ssh \
     libgl1-mesa-dev \
     libgl1-mesa-glx \
     libglew-dev \

README.md

@@ -39,7 +39,7 @@ All *seals* environments are available in the Gym registry. Simply import it and
 would with your usual RL or specification learning algroithm:
 
 ```python
-import gym
+import gymnasium as gym
 import seals
 
 env = gym.make('seals/CartPole-v0')

ci/Xdummy-entrypoint.py

@@ -1,4 +1,4 @@
-#!/usr/bin/python
+#!/usr/bin/python3
 
 # Adapted from https://github.com/openai/mujoco-py/blob/master/vendor/Xdummy-entrypoint
 # Copyright OpenAI; MIT License

pyproject.toml

@@ -6,8 +6,5 @@ build-backend = "setuptools.build_meta"
 target-version = ["py38"]
 
 [[tool.mypy.overrides]]
-module = [
-    "gym.*",
-    "setuptools_scm.*",
-]
+module = ["gym.*", "setuptools_scm.*"]
 ignore_missing_imports = true

setup.py

@@ -88,9 +88,10 @@ def get_readme() -> str:
 
 ATARI_REQUIRE = [
     "opencv-python",
-    "ale-py==0.7.4",
+    "ale-py~=0.8.1",
     "pillow",
     "autorom[accept-rom-license]~=0.4.2",
+    "shimmy[atari] >=0.1.0,<1.0",
 ]
 TESTS_REQUIRE = [
     # remove pin once https://github.com/nedbat/coveragepy/issues/881 fixed
@@ -115,11 +116,11 @@ def get_readme() -> str:
     "pytest-xdist",
     "pytype",
     "stable-baselines3>=0.9.0",
-    # TODO(adam): remove pyglet pin once Gym upgraded to >0.21
-    # Workaround for https://github.com/openai/gym/issues/2986
-    # Discussed in https://github.com/HumanCompatibleAI/imitation/pull/603
-    "pyglet==1.5.27",
     "setuptools_scm~=7.0.5",
+    # We'd like to specify `gymnasium[classic-control]`, but this is a no-op when
+    # gymnasium is already installed. See https://github.com/pypa/pip/issues/4957 for
+    # issue.
+    "pygame>=2.1.3",
     *ATARI_REQUIRE,
 ]
 DOCS_REQUIRE = [
@@ -140,16 +141,16 @@ def get_readme() -> str:
     packages=find_packages("src"),
     package_dir={"": "src"},
     package_data={"seals": ["py.typed"]},
-    install_requires=["gym", "numpy"],
+    install_requires=["gymnasium", "numpy"],
     tests_require=TESTS_REQUIRE,
     extras_require={
         # recommended packages for development
         "dev": ["ipdb", "jupyter", *TESTS_REQUIRE, *DOCS_REQUIRE],
         "docs": DOCS_REQUIRE,
         "test": TESTS_REQUIRE,
-        # We'd like to specify `gym[mujoco]`, but this is a no-op when Gym is already
-        # installed. See https://github.com/pypa/pip/issues/4957 for issue.
-        "mujoco": ["mujoco_py>=1.50, <2.0", "imageio"],
+        # We'd like to specify `gymnasium[mujoco]`, but this is a no-op when gymnasium
+        # is already installed. See https://github.com/pypa/pip/issues/4957 for issue.
+        "mujoco": ["mujoco", "imageio"],
         "atari": ATARI_REQUIRE,
     },
     url="https://github.com/HumanCompatibleAI/benchmark-environments",

src/seals/__init__.py

@@ -2,7 +2,7 @@
 
 from importlib import metadata
 
-import gym
+import gymnasium as gym
 
 from seals import atari, util
 import seals.diagnostics  # noqa: F401
@@ -31,12 +31,12 @@
 
 for env_base in ["Ant", "HalfCheetah", "Hopper", "Humanoid", "Swimmer", "Walker2d"]:
     gym.register(
-        id=f"seals/{env_base}-v0",
+        id=f"seals/{env_base}-v1",
         entry_point=f"seals.mujoco:{env_base}Env",
-        max_episode_steps=util.get_gym_max_episode_steps(f"{env_base}-v3"),
+        max_episode_steps=util.get_gym_max_episode_steps(f"{env_base}-v4"),
     )
 
 # Atari
 
-GYM_ATARI_ENV_SPECS = list(filter(atari._supported_atari_env, gym.envs.registry.all()))
+GYM_ATARI_ENV_SPECS = list(filter(atari._supported_atari_env, gym.registry.values()))
 atari.register_atari_envs(GYM_ATARI_ENV_SPECS)

src/seals/atari.py

@@ -2,7 +2,8 @@
 
 from typing import Dict, Iterable, Optional
 
-import gym
+import gymnasium as gym
+from gymnasium.envs.registration import EnvSpec
 
 from seals.util import (
     AutoResetWrapper,
@@ -35,9 +36,9 @@ def _get_score_region(atari_env_id: str) -> Optional[MaskedRegionSpecifier]:
     return SCORE_REGIONS.get(basename)
 
 
-def make_atari_env(atari_env_id: str, masked: bool) -> gym.Env:
+def make_atari_env(atari_env_id: str, masked: bool, *args, **kwargs) -> gym.Env:
     """Fixed-length, optionally masked-score variant of a given Atari environment."""
-    env = AutoResetWrapper(gym.make(atari_env_id))
+    env: gym.Env = AutoResetWrapper(gym.make(atari_env_id, *args, **kwargs))
 
     if masked:
         score_region = _get_score_region(atari_env_id)
@@ -59,15 +60,15 @@ def _not_ram_or_det(env_id: str) -> bool:
     after_slash = slash_separated[-1]
     hyphen_separated = after_slash.split("-")
     assert len(hyphen_separated) > 1
-    not_ram = not ("ram" in hyphen_separated[1])
-    not_deterministic = not ("Deterministic" in env_id)
+    not_ram = "ram" not in hyphen_separated[1]
+    not_deterministic = "Deterministic" not in env_id
     return not_ram and not_deterministic
 
 
-def _supported_atari_env(gym_spec: gym.envs.registration.EnvSpec) -> bool:
+def _supported_atari_env(gym_spec: EnvSpec) -> bool:
     """Checks if a gym Atari environment is one of the ones we will support."""
-    is_atari = gym_spec.entry_point == "gym.envs.atari:AtariEnv"
-    v5_and_plain = gym_spec.id.endswith("-v5") and not ("NoFrameskip" in gym_spec.id)
+    is_atari = gym_spec.entry_point == "shimmy.atari_env:AtariEnv"
+    v5_and_plain = gym_spec.id.endswith("-v5") and "NoFrameskip" not in gym_spec.id
     v4_and_no_frameskip = gym_spec.id.endswith("-v4") and "NoFrameskip" in gym_spec.id
     return (
         is_atari
@@ -76,7 +77,7 @@ def _supported_atari_env(gym_spec: gym.envs.registration.EnvSpec) -> bool:
     )
 
 
-def _seals_name(gym_spec: gym.envs.registration.EnvSpec, masked: bool) -> str:
+def _seals_name(gym_spec: EnvSpec, masked: bool) -> str:
     """Makes a Gym ID for an Atari environment in the seals namespace."""
     slash_separated = gym_spec.id.split("/")
     name = "seals/" + slash_separated[-1]
@@ -88,7 +89,7 @@ def _seals_name(gym_spec: gym.envs.registration.EnvSpec, masked: bool) -> str:
 
 
 def register_atari_envs(
-    gym_atari_env_specs: Iterable[gym.envs.registration.EnvSpec],
+    gym_atari_env_specs: Iterable[EnvSpec],
 ) -> None:
     """Register masked and unmasked wrapped gym Atari environments."""