forked from google-deepmind/dm_env
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path_environment_test.py
More file actions
88 lines (76 loc) · 3.61 KB
/
Copy path_environment_test.py
File metadata and controls
88 lines (76 loc) · 3.61 KB
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
# pylint: disable=g-bad-file-header
# Copyright 2019 The dm_env Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Tests for dm_env._environment."""
from absl.testing import absltest
from absl.testing import parameterized
import dm_env
class TimeStepHelpersTest(parameterized.TestCase):
@parameterized.parameters(dict(observation=-1), dict(observation=[2., 3.]))
def test_restart(self, observation):
time_step = dm_env.restart(observation)
self.assertIs(dm_env.StepType.FIRST, time_step.step_type)
self.assertEqual(observation, time_step.observation)
self.assertIsNone(time_step.reward)
self.assertIsNone(time_step.discount)
@parameterized.parameters(
dict(observation=-1., reward=2.0, discount=1.0),
dict(observation=(2., 3.), reward=0., discount=0.))
def test_transition(self, observation, reward, discount):
time_step = dm_env.transition(
reward=reward, observation=observation, discount=discount)
self.assertIs(dm_env.StepType.MID, time_step.step_type)
self.assertEqual(observation, time_step.observation)
self.assertEqual(reward, time_step.reward)
self.assertEqual(discount, time_step.discount)
@parameterized.parameters(
dict(observation=-1., reward=2.0),
dict(observation=(2., 3.), reward=0.))
def test_termination(self, observation, reward):
time_step = dm_env.termination(reward=reward, observation=observation)
self.assertIs(dm_env.StepType.LAST, time_step.step_type)
self.assertEqual(observation, time_step.observation)
self.assertEqual(reward, time_step.reward)
self.assertEqual(0.0, time_step.discount)
@parameterized.parameters(
dict(observation=-1., reward=2.0, discount=1.0),
dict(observation=(2., 3.), reward=0., discount=0.))
def test_truncation(self, reward, observation, discount):
time_step = dm_env.truncation(reward, observation, discount)
self.assertIs(dm_env.StepType.LAST, time_step.step_type)
self.assertEqual(observation, time_step.observation)
self.assertEqual(reward, time_step.reward)
self.assertEqual(discount, time_step.discount)
@parameterized.parameters(
dict(step_type=dm_env.StepType.FIRST,
is_first=True, is_mid=False, is_last=False),
dict(step_type=dm_env.StepType.MID,
is_first=False, is_mid=True, is_last=False),
dict(step_type=dm_env.StepType.LAST,
is_first=False, is_mid=False, is_last=True),
)
def test_step_type_helpers(self, step_type, is_first, is_mid, is_last):
time_step = dm_env.TimeStep(
reward=None, discount=None, observation=None, step_type=step_type)
with self.subTest('TimeStep methods'):
self.assertEqual(is_first, time_step.first())
self.assertEqual(is_mid, time_step.mid())
self.assertEqual(is_last, time_step.last())
with self.subTest('StepType methods'):
self.assertEqual(is_first, time_step.step_type.first())
self.assertEqual(is_mid, time_step.step_type.mid())
self.assertEqual(is_last, time_step.step_type.last())
if __name__ == '__main__':
absltest.main()