dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch '47-update-to-new-gym-api' into gym_upgrade

Browse Source
This commit is contained in:
dodox
2023-05-15 17:19:50 +02:00
parent 826f22b18e c53924d9fc
commit 228e343a1b
42 changed files with 464 additions and 490 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/test_dmc_envs.py
+27 -21
View File
@@ -1,48 +1,54 @@
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')]
DMC_MP_IDS = chain(*fancy_gym.ALL_DMC_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values())
# 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
spec.id.startswith('dm_control/')
and 'compatibility-env-v0' not in spec.id
and 'lqr-lqr' not in spec.id]
DM_control_MP_IDS = list(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)
run_env(env_id, 5000, wrappers=[gym.wrappers.FlattenObservation])
@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)
run_env_determinism(env_id, SEED, 5000, wrappers=[gym.wrappers.FlattenObservation])
@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_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_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)
@pytest.mark.parametrize('env_id', DM_control_MP_IDS)
def test_bb_dmc_functionality(env_id: str):
"""Tests that black box environments run without errors using random actions."""
run_env(env_id)
@pytest.mark.parametrize('env_id', DMC_MP_IDS)
@pytest.mark.parametrize('env_id', DM_control_MP_IDS)
def test_bb_dmc_determinism(env_id: str):
"""Tests that for black box environment identical seeds produce identical trajectories."""
run_env_determinism(env_id, SEED)
test/test_fancy_envs.py
+6 -4
View File
@@ -1,14 +1,16 @@
import itertools
from itertools import chain
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 = [spec.id for spec in gym.envs.registry.all() if
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())
CUSTOM_MP_IDS = list(chain(*fancy_gym.ALL_FANCY_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values()))
SEED = 1
test/test_gym_envs.py
+10 -4
View File
@@ -1,14 +1,20 @@
import re
from itertools import chain
from typing import Callable
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
"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())
GYM_IDS = [spec.id for spec in gym.envs.registry.values() if
not isinstance(spec.entry_point, Callable) and
"fancy_gym" not in spec.entry_point and 'make_bb_env_helper' not in spec.entry_point
and 'jax' not in spec.id.lower()
and not re.match(r'GymV2.Environment', spec.id)
]
GYM_MP_IDS = list(chain(*fancy_gym.ALL_DMC_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values()))
SEED = 1
test/test_metaworld_envs.py
+4
View File
@@ -8,7 +8,11 @@ from test.utils import run_env, run_env_determinism
METAWORLD_IDS = [f'metaworld:{env.split("-goal-observable")[0]}' for env, _ in
ALL_V2_ENVIRONMENTS_GOAL_OBSERVABLE.items()]
<<<<<<< HEAD
METAWORLD_MP_IDS = chain(*fancy_gym.ALL_METAWORLD_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values())
=======
METAWORLD_MP_IDS = list(chain(*fancy_gym.ALL_METAWORLD_MOVEMENT_PRIMITIVE_ENVIRONMENTS.values()))
>>>>>>> 47-update-to-new-gym-api
SEED = 1
test/utils.py
+41 -21
View File
@@ -1,9 +1,12 @@
import gym
from typing import List, Type
import gymnasium as gym
import numpy as np
from fancy_gym import make
def run_env(env_id, iterations=None, seed=0, render=False):
def run_env(env_id: str, iterations: int = None, seed: int = 0, wrappers: List[Type[gym.Wrapper]] = [],
render: bool = False):
"""
Example for running a DMC based env in the step based setting.
The env_id has to be specified as `dmc:domain_name-task_name` or
@@ -13,17 +16,21 @@ def run_env(env_id, iterations=None, seed=0, render=False):
env_id: Either `dmc:domain_name-task_name` or `dmc:manipulation-environment_name`
iterations: Number of rollout steps to run
seed: random seeding
wrappers: List of Wrappers to apply to the environment
render: Render the episode
Returns: observations, rewards, dones, actions
Returns: observations, rewards, terminations, truncations, actions
"""
env: gym.Env = make(env_id, seed=seed)
for w in wrappers:
env = w(env)
rewards = []
observations = []
actions = []
dones = []
obs = env.reset()
terminations = []
truncations = []
obs, _ = env.reset()
verify_observations(obs, env.observation_space, "reset()")
iterations = iterations or (env.spec.max_episode_steps or 1)
@@ -35,38 +42,49 @@ 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
if not hasattr(env, "replanning_schedule"):
assert done, "Done flag is not True after end of episode."
assert terminated or truncated, f"Termination or truncation flag is not True after {i + 1} iterations."
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):
traj1 = run_env(env_id, seed=seed)
traj2 = run_env(env_id, seed=seed)
def run_env_determinism(env_id: str, seed: int, iterations: int = None, wrappers: List[Type[gym.Wrapper]] = []):
traj1 = run_env(env_id, iterations=iterations,
seed=seed, wrappers=wrappers)
traj2 = run_env(env_id, iterations=iterations,
seed=seed, wrappers=wrappers)
# 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
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."
obs1, rwd1, term1, trunc1, ac1, obs2, rwd2, term2, trunc2, ac2 = time_step
assert np.allclose(
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(
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()"):
@@ -75,8 +93,10 @@ def verify_observations(obs, observation_space: gym.Space, obs_type="reset()"):
def verify_reward(reward):
assert isinstance(reward, (float, int)), f"Returned type {type(reward)} as reward, expected float or int."
assert isinstance(
reward, (float, int)), f"Returned type {type(reward)} as reward, expected float or int."
def verify_done(done):
assert isinstance(done, bool), f"Returned {done} as done flag, expected bool."
assert isinstance(
done, bool), f"Returned {done} as done flag, expected bool."