updated examples to new api,

test/test_dmc_envs.py

@@ -1,39 +1,43 @@
 from itertools import chain
+from typing import Callable
 
+import gymnasium as gym
 import pytest
 from dm_control import suite, manipulation
 
 import fancy_gym
 from test.utils import run_env, run_env_determinism
 
-SUITE_IDS = [f'dmc:{env}-{task}' for env, task in suite.ALL_TASKS if env != "lqr"]
-MANIPULATION_IDS = [f'dmc:manipulation-{task}' for task in manipulation.ALL if task.endswith('_features')]
+# SUITE_IDS = [f'dmc:{env}-{task}' for env, task in suite.ALL_TASKS if env != "lqr"]
+# MANIPULATION_IDS = [f'dmc:manipulation-{task}' for task in manipulation.ALL if task.endswith('_features')]
+DM_CONTROL_IDS = [spec.id for spec in gym.envs.registry.values() if
+                  not isinstance(spec.entry_point, Callable) and spec.entry_point.startswith('dm_control/')]
 DMC_MP_IDS = chain(*fancy_gym.ALL_DMC_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values())
 SEED = 1
 
 
-@pytest.mark.parametrize('env_id', SUITE_IDS)
-def test_step_suite_functionality(env_id: str):
+@pytest.mark.parametrize('env_id', DM_CONTROL_IDS)
+def test_step_dm_control_functionality(env_id: str):
     """Tests that suite step environments run without errors using random actions."""
     run_env(env_id)
 
 
-@pytest.mark.parametrize('env_id', SUITE_IDS)
-def test_step_suite_determinism(env_id: str):
+@pytest.mark.parametrize('env_id', DM_CONTROL_IDS)
+def test_step_dm_control_determinism(env_id: str):
     """Tests that for step environments identical seeds produce identical trajectories."""
     run_env_determinism(env_id, SEED)
 
 
-@pytest.mark.parametrize('env_id', MANIPULATION_IDS)
-def test_step_manipulation_functionality(env_id: str):
-    """Tests that manipulation step environments run without errors using random actions."""
-    run_env(env_id)
-
-
-@pytest.mark.parametrize('env_id', MANIPULATION_IDS)
-def test_step_manipulation_determinism(env_id: str):
-    """Tests that for step environments identical seeds produce identical trajectories."""
-    run_env_determinism(env_id, SEED)
+# @pytest.mark.parametrize('env_id', MANIPULATION_IDS)
+# def test_step_manipulation_functionality(env_id: str):
+#     """Tests that manipulation step environments run without errors using random actions."""
+#     run_env(env_id)
+#
+#
+# @pytest.mark.parametrize('env_id', MANIPULATION_IDS)
+# def test_step_manipulation_determinism(env_id: str):
+#     """Tests that for step environments identical seeds produce identical trajectories."""
+#     run_env_determinism(env_id, SEED)
 
 
 @pytest.mark.parametrize('env_id', DMC_MP_IDS)

test/test_fancy_envs.py

@@ -1,12 +1,14 @@
 import itertools
+from typing import Callable
 
 import fancy_gym
-import gym
+import gymnasium as gym
 import pytest
 
 from test.utils import run_env, run_env_determinism
 
 CUSTOM_IDS = [id for id, spec in gym.envs.registry.items() if
+              not isinstance(spec.entry_point, Callable) and
               "fancy_gym" in spec.entry_point and 'make_bb_env_helper' not in spec.entry_point]
 CUSTOM_MP_IDS = itertools.chain(*fancy_gym.ALL_FANCY_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values())
 SEED = 1

test/test_gym_envs.py

@@ -1,12 +1,12 @@
 from itertools import chain
 
-import gym
+import gymnasium as gym
 import pytest
 
 import fancy_gym
 from test.utils import run_env, run_env_determinism
 
-GYM_IDS = [spec.id for spec in gym.envs.registry.all() if
+GYM_IDS = [spec.id for spec in gym.envs.registry.values() if
            "fancy_gym" not in spec.entry_point and 'make_bb_env_helper' not in spec.entry_point]
 GYM_MP_IDS = chain(*fancy_gym.ALL_DMC_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values())
 SEED = 1

test/utils.py

@@ -1,4 +1,4 @@
-import gym
+import gymnasium as gym
 import numpy as np
 from fancy_gym import make
 
@@ -15,16 +15,16 @@ def run_env(env_id, iterations=None, seed=0, render=False):
         seed: random seeding
         render: Render the episode
 
-    Returns: observations, rewards, dones, actions
+    Returns: observations, rewards, terminations, truncations, actions
 
     """
     env: gym.Env = make(env_id, seed=seed)
     rewards = []
     observations = []
     actions = []
-    dones = []
-    obs = env.reset()
-    print(obs.dtype)
+    terminations = []
+    truncations = []
+    obs, _ = env.reset()
     verify_observations(obs, env.observation_space, "reset()")
 
     iterations = iterations or (env.spec.max_episode_steps or 1)
@@ -36,26 +36,28 @@ def run_env(env_id, iterations=None, seed=0, render=False):
         ac = env.action_space.sample()
         actions.append(ac)
         # ac = np.random.uniform(env.action_space.low, env.action_space.high, env.action_space.shape)
-        obs, reward, done, info = env.step(ac)
+        obs, reward, terminated, truncated, info = env.step(ac)
 
         verify_observations(obs, env.observation_space, "step()")
         verify_reward(reward)
-        verify_done(done)
+        verify_done(terminated)
+        verify_done(truncated)
 
         rewards.append(reward)
-        dones.append(done)
+        terminations.append(terminated)
+        truncations.append(truncated)
 
         if render:
             env.render("human")
 
-        if done:
+        if terminated or truncated:
             break
 
-    assert done, "Done flag is not True after end of episode."
+    assert terminated or truncated, "Termination or truncation flag is not True after end of episode."
     observations.append(obs)
     env.close()
     del env
-    return np.array(observations), np.array(rewards), np.array(dones), np.array(actions)
+    return np.array(observations), np.array(rewards), np.array(terminations), np.array(truncations), np.array(actions)
 
 
 def run_env_determinism(env_id: str, seed: int):
@@ -63,11 +65,12 @@ def run_env_determinism(env_id: str, seed: int):
     traj2 = run_env(env_id, seed=seed)
     # Iterate over two trajectories, which should have the same state and action sequence
     for i, time_step in enumerate(zip(*traj1, *traj2)):
-        obs1, rwd1, done1, ac1, obs2, rwd2, done2, ac2 = time_step
+        obs1, rwd1, term1, trunc1, ac1, obs2, rwd2, term2, trunc2, ac2 = time_step
         assert np.array_equal(obs1, obs2), f"Observations [{i}] {obs1} and {obs2} do not match."
         assert np.array_equal(ac1, ac2), f"Actions [{i}] {ac1} and {ac2} do not match."
         assert np.array_equal(rwd1, rwd2), f"Rewards [{i}] {rwd1} and {rwd2} do not match."
-        assert np.array_equal(done1, done2), f"Dones [{i}] {done1} and {done2} do not match."
+        assert np.array_equal(term1, term2), f"Terminateds [{i}] {term1} and {term2} do not match."
+        assert np.array_equal(term1, term2), f"Truncateds [{i}] {trunc1} and {trunc2} do not match."
 
 
 def verify_observations(obs, observation_space: gym.Space, obs_type="reset()"):