File size: 10,414 Bytes
05c9ac2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
from unittest import mock
import pytest
import numpy as np
from gym import spaces
from mlagents_envs.envs.unity_gym_env import UnityToGymWrapper
from mlagents_envs.base_env import (
BehaviorSpec,
ActionSpec,
DecisionSteps,
TerminalSteps,
BehaviorMapping,
)
from dummy_config import create_observation_specs_with_shapes
def test_gym_wrapper():
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec()
mock_decision_step, mock_terminal_step = create_mock_vector_steps(mock_spec)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env)
assert isinstance(env.reset(), np.ndarray)
actions = env.action_space.sample()
assert actions.shape[0] == 2
obs, rew, done, info = env.step(actions)
assert env.observation_space.contains(obs)
assert isinstance(obs, np.ndarray)
assert isinstance(rew, float)
assert isinstance(done, (bool, np.bool_))
assert isinstance(info, dict)
def test_branched_flatten():
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec(
vector_action_space_type="discrete", vector_action_space_size=[2, 2, 3]
)
mock_decision_step, mock_terminal_step = create_mock_vector_steps(
mock_spec, num_agents=1
)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env, flatten_branched=True)
assert isinstance(env.action_space, spaces.Discrete)
assert env.action_space.n == 12
assert env._flattener.lookup_action(0) == [0, 0, 0]
assert env._flattener.lookup_action(11) == [1, 1, 2]
# Check that False produces a MultiDiscrete
env = UnityToGymWrapper(mock_env, flatten_branched=False)
assert isinstance(env.action_space, spaces.MultiDiscrete)
def test_action_space():
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec(
vector_action_space_type="discrete", vector_action_space_size=[5]
)
mock_decision_step, mock_terminal_step = create_mock_vector_steps(
mock_spec, num_agents=1
)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env, flatten_branched=True)
assert isinstance(env.action_space, spaces.Discrete)
assert env.action_space.n == 5
env = UnityToGymWrapper(mock_env, flatten_branched=False)
assert isinstance(env.action_space, spaces.Discrete)
assert env.action_space.n == 5
def test_action_space_seed():
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec()
mock_decision_step, mock_terminal_step = create_mock_vector_steps(mock_spec)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
actions = []
for _ in range(0, 2):
env = UnityToGymWrapper(mock_env, action_space_seed=1337)
env.reset()
actions.append(env.action_space.sample())
assert (actions[0] == actions[1]).all()
@pytest.mark.parametrize("use_uint8", [True, False], ids=["float", "uint8"])
def test_gym_wrapper_visual(use_uint8):
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec(
number_visual_observations=1, vector_observation_space_size=0
)
mock_decision_step, mock_terminal_step = create_mock_vector_steps(
mock_spec, number_visual_observations=1
)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env, uint8_visual=use_uint8)
assert isinstance(env.observation_space, spaces.Box)
assert isinstance(env.reset(), np.ndarray)
actions = env.action_space.sample()
assert actions.shape[0] == 2
obs, rew, done, info = env.step(actions)
assert env.observation_space.contains(obs)
assert isinstance(obs, np.ndarray)
assert isinstance(rew, float)
assert isinstance(done, (bool, np.bool_))
assert isinstance(info, dict)
@pytest.mark.parametrize("use_uint8", [True, False], ids=["float", "uint8"])
def test_gym_wrapper_single_visual_and_vector(use_uint8):
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec(
number_visual_observations=1,
vector_observation_space_size=3,
vector_action_space_size=[2],
)
mock_decision_step, mock_terminal_step = create_mock_vector_steps(
mock_spec, number_visual_observations=1
)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env, uint8_visual=use_uint8, allow_multiple_obs=True)
assert isinstance(env.observation_space, spaces.Tuple)
assert len(env.observation_space) == 2
reset_obs = env.reset()
assert isinstance(reset_obs, list)
assert len(reset_obs) == 2
assert all(isinstance(ob, np.ndarray) for ob in reset_obs)
assert reset_obs[-1].shape == (3,)
assert len(reset_obs[0].shape) == 3
actions = env.action_space.sample()
assert actions.shape == (2,)
obs, rew, done, info = env.step(actions)
assert isinstance(obs, list)
assert len(obs) == 2
assert all(isinstance(ob, np.ndarray) for ob in obs)
assert reset_obs[-1].shape == (3,)
assert isinstance(rew, float)
assert isinstance(done, (bool, np.bool_))
assert isinstance(info, dict)
# check behavior for allow_multiple_obs = False
env = UnityToGymWrapper(mock_env, uint8_visual=use_uint8, allow_multiple_obs=False)
assert isinstance(env.observation_space, spaces.Box)
reset_obs = env.reset()
assert isinstance(reset_obs, np.ndarray)
assert len(reset_obs.shape) == 3
actions = env.action_space.sample()
assert actions.shape == (2,)
obs, rew, done, info = env.step(actions)
assert isinstance(obs, np.ndarray)
@pytest.mark.parametrize("use_uint8", [True, False], ids=["float", "uint8"])
def test_gym_wrapper_multi_visual_and_vector(use_uint8):
mock_env = mock.MagicMock()
mock_spec = create_mock_group_spec(
number_visual_observations=2,
vector_observation_space_size=3,
vector_action_space_size=[2],
)
mock_decision_step, mock_terminal_step = create_mock_vector_steps(
mock_spec, number_visual_observations=2
)
setup_mock_unityenvironment(
mock_env, mock_spec, mock_decision_step, mock_terminal_step
)
env = UnityToGymWrapper(mock_env, uint8_visual=use_uint8, allow_multiple_obs=True)
assert isinstance(env.observation_space, spaces.Tuple)
assert len(env.observation_space) == 3
reset_obs = env.reset()
assert isinstance(reset_obs, list)
assert len(reset_obs) == 3
assert all(isinstance(ob, np.ndarray) for ob in reset_obs)
assert reset_obs[-1].shape == (3,)
actions = env.action_space.sample()
assert actions.shape == (2,)
obs, rew, done, info = env.step(actions)
assert all(isinstance(ob, np.ndarray) for ob in obs)
assert isinstance(rew, float)
assert isinstance(done, (bool, np.bool_))
assert isinstance(info, dict)
# check behavior for allow_multiple_obs = False
env = UnityToGymWrapper(mock_env, uint8_visual=use_uint8, allow_multiple_obs=False)
assert isinstance(env.observation_space, spaces.Box)
reset_obs = env.reset()
assert isinstance(reset_obs, np.ndarray)
assert len(reset_obs.shape) == 3
actions = env.action_space.sample()
assert actions.shape == (2,)
obs, rew, done, info = env.step(actions)
assert isinstance(obs, np.ndarray)
# Helper methods
def create_mock_group_spec(
number_visual_observations=0,
vector_action_space_type="continuous",
vector_observation_space_size=3,
vector_action_space_size=None,
):
"""
Creates a mock BrainParameters object with parameters.
"""
# Avoid using mutable object as default param
if vector_action_space_type == "continuous":
if vector_action_space_size is None:
vector_action_space_size = 2
else:
vector_action_space_size = vector_action_space_size[0]
action_spec = ActionSpec.create_continuous(vector_action_space_size)
else:
if vector_action_space_size is None:
vector_action_space_size = (2,)
else:
vector_action_space_size = tuple(vector_action_space_size)
action_spec = ActionSpec.create_discrete(vector_action_space_size)
obs_shapes = [(vector_observation_space_size,)]
for _ in range(number_visual_observations):
obs_shapes += [(8, 8, 3)]
obs_spec = create_observation_specs_with_shapes(obs_shapes)
return BehaviorSpec(obs_spec, action_spec)
def create_mock_vector_steps(specs, num_agents=1, number_visual_observations=0):
"""
Creates a mock BatchedStepResult with vector observations. Imitates constant
vector observations, rewards, dones, and agents.
:BehaviorSpecs specs: The BehaviorSpecs for this mock
:int num_agents: Number of "agents" to imitate in your BatchedStepResult values.
"""
obs = [np.array([num_agents * [1, 2, 3]], dtype=np.float32).reshape(num_agents, 3)]
if number_visual_observations:
obs += [
np.zeros(shape=(num_agents, 8, 8, 3), dtype=np.float32)
] * number_visual_observations
rewards = np.array(num_agents * [1.0])
agents = np.array(range(0, num_agents))
group_id = np.array(num_agents * [0])
group_rewards = np.array(num_agents * [0.0])
return (
DecisionSteps(obs, rewards, agents, None, group_id, group_rewards),
TerminalSteps.empty(specs),
)
def setup_mock_unityenvironment(mock_env, mock_spec, mock_decision, mock_termination):
"""
Takes a mock UnityEnvironment and adds the appropriate properties, defined by the mock
GroupSpec and BatchedStepResult.
:Mock mock_env: A mock UnityEnvironment, usually empty.
:Mock mock_spec: An AgentGroupSpec object that specifies the params of this environment.
:Mock mock_decision: A DecisionSteps object that will be returned at each step and reset.
:Mock mock_termination: A TerminationSteps object that will be returned at each step and reset.
"""
mock_env.behavior_specs = BehaviorMapping({"MockBrain": mock_spec})
mock_env.get_steps.return_value = (mock_decision, mock_termination)
|