File size: 7,982 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
using System.Collections.Generic;
using NUnit.Framework;
using Unity.Barracuda;
using Unity.MLAgents.Actuators;
using Unity.MLAgents.Inference;

namespace Unity.MLAgents.Tests
{
    public class EditModeTestInternalBrainTensorApplier
    {
        class TestAgent : Agent
        {
        }

        [Test]
        public void Construction()
        {
            var actionSpec = new ActionSpec();
            var alloc = new TensorCachingAllocator();
            var mem = new Dictionary<int, List<float>>();
            var tensorGenerator = new TensorApplier(actionSpec, 0, alloc, mem);
            Assert.IsNotNull(tensorGenerator);
            alloc.Dispose();
        }

        [Test]
        public void ApplyContinuousActionOutput()
        {
            var actionSpec = ActionSpec.MakeContinuous(3);
            var inputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 3 },
                data = new Tensor(2, 3, new float[] { 1, 2, 3, 4, 5, 6 })
            };

            var applier = new ContinuousActionOutputApplier(actionSpec);

            var agentIds = new List<int>() { 0, 1 };
            // Dictionary from AgentId to Action
            var actionDict = new Dictionary<int, ActionBuffers>() { { 0, ActionBuffers.Empty }, { 1, ActionBuffers.Empty } };

            applier.Apply(inputTensor, agentIds, actionDict);


            Assert.AreEqual(actionDict[0].ContinuousActions[0], 1);
            Assert.AreEqual(actionDict[0].ContinuousActions[1], 2);
            Assert.AreEqual(actionDict[0].ContinuousActions[2], 3);

            Assert.AreEqual(actionDict[1].ContinuousActions[0], 4);
            Assert.AreEqual(actionDict[1].ContinuousActions[1], 5);
            Assert.AreEqual(actionDict[1].ContinuousActions[2], 6);
        }

        [Test]
        public void ApplyDiscreteActionOutputLegacy()
        {
            var actionSpec = ActionSpec.MakeDiscrete(2, 3);
            var inputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 5 },
                data = new Tensor(
                    2,
                    5,
                    new[] { 0.5f, 22.5f, 0.1f, 5f, 1f, 4f, 5f, 6f, 7f, 8f })
            };
            var alloc = new TensorCachingAllocator();
            var applier = new LegacyDiscreteActionOutputApplier(actionSpec, 0, alloc);

            var agentIds = new List<int>() { 0, 1 };
            // Dictionary from AgentId to Action
            var actionDict = new Dictionary<int, ActionBuffers>() { { 0, ActionBuffers.Empty }, { 1, ActionBuffers.Empty } };


            applier.Apply(inputTensor, agentIds, actionDict);

            Assert.AreEqual(actionDict[0].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[0].DiscreteActions[1], 1);

            Assert.AreEqual(actionDict[1].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[1].DiscreteActions[1], 2);
            alloc.Dispose();
        }

        [Test]
        public void ApplyDiscreteActionOutput()
        {
            var actionSpec = ActionSpec.MakeDiscrete(2, 3);
            var inputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 2 },
                data = new Tensor(
                    2,
                    2,
                    new[] { 1f, 1f, 1f, 2f }),
            };
            var alloc = new TensorCachingAllocator();
            var applier = new DiscreteActionOutputApplier(actionSpec, 0, alloc);

            var agentIds = new List<int>() { 0, 1 };
            // Dictionary from AgentId to Action
            var actionDict = new Dictionary<int, ActionBuffers>() { { 0, ActionBuffers.Empty }, { 1, ActionBuffers.Empty } };


            applier.Apply(inputTensor, agentIds, actionDict);

            Assert.AreEqual(actionDict[0].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[0].DiscreteActions[1], 1);

            Assert.AreEqual(actionDict[1].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[1].DiscreteActions[1], 2);
            alloc.Dispose();
        }

        [Test]
        public void ApplyHybridActionOutputLegacy()
        {
            var actionSpec = new ActionSpec(3, new[] { 2, 3 });
            var continuousInputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 3 },
                data = new Tensor(2, 3, new float[] { 1, 2, 3, 4, 5, 6 })
            };
            var discreteInputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 8 },
                data = new Tensor(
                    2,
                    5,
                    new[] { 0.5f, 22.5f, 0.1f, 5f, 1f, 4f, 5f, 6f, 7f, 8f })
            };
            var continuousApplier = new ContinuousActionOutputApplier(actionSpec);
            var alloc = new TensorCachingAllocator();
            var discreteApplier = new LegacyDiscreteActionOutputApplier(actionSpec, 0, alloc);

            var agentIds = new List<int>() { 0, 1 };
            // Dictionary from AgentId to Action
            var actionDict = new Dictionary<int, ActionBuffers>() { { 0, ActionBuffers.Empty }, { 1, ActionBuffers.Empty } };


            continuousApplier.Apply(continuousInputTensor, agentIds, actionDict);
            discreteApplier.Apply(discreteInputTensor, agentIds, actionDict);

            Assert.AreEqual(actionDict[0].ContinuousActions[0], 1);
            Assert.AreEqual(actionDict[0].ContinuousActions[1], 2);
            Assert.AreEqual(actionDict[0].ContinuousActions[2], 3);
            Assert.AreEqual(actionDict[0].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[0].DiscreteActions[1], 1);

            Assert.AreEqual(actionDict[1].ContinuousActions[0], 4);
            Assert.AreEqual(actionDict[1].ContinuousActions[1], 5);
            Assert.AreEqual(actionDict[1].ContinuousActions[2], 6);
            Assert.AreEqual(actionDict[1].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[1].DiscreteActions[1], 2);
            alloc.Dispose();
        }

        [Test]
        public void ApplyHybridActionOutput()
        {
            var actionSpec = new ActionSpec(3, new[] { 2, 3 });
            var continuousInputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 3 },
                data = new Tensor(2, 3, new float[] { 1, 2, 3, 4, 5, 6 })
            };
            var discreteInputTensor = new TensorProxy()
            {
                shape = new long[] { 2, 2 },
                data = new Tensor(
                    2,
                    2,
                    new[] { 1f, 1f, 1f, 2f }),
            };
            var continuousApplier = new ContinuousActionOutputApplier(actionSpec);
            var alloc = new TensorCachingAllocator();
            var discreteApplier = new DiscreteActionOutputApplier(actionSpec, 0, alloc);

            var agentIds = new List<int>() { 0, 1 };
            // Dictionary from AgentId to Action
            var actionDict = new Dictionary<int, ActionBuffers>() { { 0, ActionBuffers.Empty }, { 1, ActionBuffers.Empty } };


            continuousApplier.Apply(continuousInputTensor, agentIds, actionDict);
            discreteApplier.Apply(discreteInputTensor, agentIds, actionDict);

            Assert.AreEqual(actionDict[0].ContinuousActions[0], 1);
            Assert.AreEqual(actionDict[0].ContinuousActions[1], 2);
            Assert.AreEqual(actionDict[0].ContinuousActions[2], 3);
            Assert.AreEqual(actionDict[0].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[0].DiscreteActions[1], 1);

            Assert.AreEqual(actionDict[1].ContinuousActions[0], 4);
            Assert.AreEqual(actionDict[1].ContinuousActions[1], 5);
            Assert.AreEqual(actionDict[1].ContinuousActions[2], 6);
            Assert.AreEqual(actionDict[1].DiscreteActions[0], 1);
            Assert.AreEqual(actionDict[1].DiscreteActions[1], 2);
            alloc.Dispose();
        }
    }
}