public void TestEvalP()
{
var m = new Multinomial(2018);
var src = new TensorProxy
{
data = new Tensor(1, 3, new[] { 0.1f, 0.2f, 0.7f }),
valueType = TensorProxy.TensorType.FloatingPoint
};
var dst = new TensorProxy
{
data = new Tensor(1, 3),
valueType = TensorProxy.TensorType.FloatingPoint
};
DiscreteActionOutputApplier.Eval(src, dst, m);
float[] reference = { 2, 2, 1 };
for (var i = 0; i < dst.data.length; i++)
{
Assert.AreEqual(reference[i], dst.data[i]);
++i;
}
}
public void TestEvalBatching()
{
var m = new Multinomial(2018);
var src = new TensorProxy
{
data = new Tensor(2, 3, new[]
{
Mathf.Log(0.1f) - 50, Mathf.Log(0.2f) - 50, Mathf.Log(0.7f) - 50,
Mathf.Log(0.3f) - 25, Mathf.Log(0.4f) - 25, Mathf.Log(0.3f) - 25
}),
valueType = TensorProxy.TensorType.FloatingPoint
};
var dst = new TensorProxy
{
data = new Tensor(2, 3),
valueType = TensorProxy.TensorType.FloatingPoint
};
DiscreteActionOutputApplier.Eval(src, dst, m);
float[] reference = { 2, 2, 2, 0, 1, 0 };
for (var i = 0; i < dst.data.length; i++)
{
Assert.AreEqual(reference[i], dst.data[i]);
++i;
}
}
public void ApplyDiscreteActionOutput()
{
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 DiscreteActionOutputApplier(new[] { 2, 3 }, 0, alloc);
var agentIds = new List<int>() { 0, 1 };
// Dictionary from AgentId to Action
var actionDict = new Dictionary<int, float[]>() { { 0, null }, { 1, null } };
applier.Apply(inputTensor, agentIds, actionDict);
Assert.AreEqual(actionDict[0][0], 1);
Assert.AreEqual(actionDict[0][1], 1);
Assert.AreEqual(actionDict[1][0], 1);
Assert.AreEqual(actionDict[1][1], 2);
alloc.Dispose();
}
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();
}
public void ApplyDiscreteActionOutput()
{
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 agentInfos = GetFakeAgentInfos();
var alloc = new TensorCachingAllocator();
var applier = new DiscreteActionOutputApplier(new[] { 2, 3 }, 0, alloc);
applier.Apply(inputTensor, agentInfos);
var agents = agentInfos;
var agent = agents[0] as TestAgent;
Assert.NotNull(agent);
var action = agent.GetAction();
Assert.AreEqual(action.vectorActions[0], 1);
Assert.AreEqual(action.vectorActions[1], 1);
agent = agents[1] as TestAgent;
Assert.NotNull(agent);
action = agent.GetAction();
Assert.AreEqual(action.vectorActions[0], 1);
Assert.AreEqual(action.vectorActions[1], 2);
alloc.Dispose();
}
public void ApplyDiscreteActionOutput()
{
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 DiscreteActionOutputApplier(new[] { 2, 3 }, 0, alloc);
var action0 = new AgentAction();
var action1 = new AgentAction();
var callbacks = new List <AgentIdActionPair>()
{
new AgentIdActionPair {
agentId = 0, action = (a) => action0 = a
},
new AgentIdActionPair {
agentId = 1, action = (a) => action1 = a
}
};
applier.Apply(inputTensor, callbacks);
Assert.AreEqual(action0.vectorActions[0], 1);
Assert.AreEqual(action0.vectorActions[1], 1);
Assert.AreEqual(action1.vectorActions[0], 1);
Assert.AreEqual(action1.vectorActions[1], 2);
alloc.Dispose();
}
public void ApplyDiscreteActionOutput()
{
var inputTensor = new Tensor()
{
Shape = new long[] { 2, 5 },
Data = new float[, ] {
{ 0.5f, 22.5f, 0.1f, 5f, 1f },
{ 4f, 5f, 6f, 7f, 8f }
}
};
var agentInfos = GetFakeAgentInfos();
var applier = new DiscreteActionOutputApplier(new int[] { 2, 3 }, 0);
applier.Apply(inputTensor, agentInfos);
var agents = agentInfos.Keys.ToList();
var agent = agents[0] as TestAgent;
var action = agent.GetAction();
Assert.AreEqual(action.vectorActions[0], 1);
Assert.AreEqual(action.vectorActions[1], 1);
agent = agents[1] as TestAgent;
action = agent.GetAction();
Assert.AreEqual(action.vectorActions[0], 1);
Assert.AreEqual(action.vectorActions[1], 2);
}
public void TestSrcInt()
{
var m = new Multinomial(2018);
var src = new TensorProxy
{
valueType = TensorProxy.TensorType.Integer
};
Assert.Throws <NotImplementedException>(
() => DiscreteActionOutputApplier.Eval(src, null, m));
}
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();
}
public void TestSrcDataNull()
{
var m = new Multinomial(2018);
var src = new TensorProxy
{
valueType = TensorProxy.TensorType.FloatingPoint
};
var dst = new TensorProxy
{
valueType = TensorProxy.TensorType.FloatingPoint
};
Assert.Throws <ArgumentNullException>(
() => DiscreteActionOutputApplier.Eval(src, dst, m));
}
public void TestUnequalBatchSize()
{
var m = new Multinomial(2018);
var src = new TensorProxy
{
valueType = TensorProxy.TensorType.FloatingPoint,
data = new Tensor(1, 1)
};
var dst = new TensorProxy
{
valueType = TensorProxy.TensorType.FloatingPoint,
data = new Tensor(2, 1)
};
Assert.Throws <ArgumentException>(
() => DiscreteActionOutputApplier.Eval(src, dst, m));
}
public void TestDiscreteApply()
{
var actionSpec = ActionSpec.MakeDiscrete(3, 2);
const float smallLogProb = -1000.0f;
const float largeLogProb = -1.0f;
var logProbs = new TensorProxy
{
data = new Tensor(
2,
5,
new[]
{
smallLogProb, smallLogProb, largeLogProb, // Agent 0, branch 0
smallLogProb, largeLogProb, // Agent 0, branch 1
largeLogProb, smallLogProb, smallLogProb, // Agent 1, branch 0
largeLogProb, smallLogProb, // Agent 1, branch 1
}),
valueType = TensorProxy.TensorType.FloatingPoint
};
var applier = new DiscreteActionOutputApplier(actionSpec, 2020, null);
var agentIds = new List <int> {
42, 1337
};
var actionBuffers = new Dictionary <int, ActionBuffers>();
actionBuffers[42] = new ActionBuffers(actionSpec);
actionBuffers[1337] = new ActionBuffers(actionSpec);
applier.Apply(logProbs, agentIds, actionBuffers);
Assert.AreEqual(2, actionBuffers[42].DiscreteActions[0]);
Assert.AreEqual(1, actionBuffers[42].DiscreteActions[1]);
Assert.AreEqual(0, actionBuffers[1337].DiscreteActions[0]);
Assert.AreEqual(0, actionBuffers[1337].DiscreteActions[1]);
}
public void TestDiscreteApply()
{
var actionSpec = ActionSpec.MakeDiscrete(3, 2);
var applier = new DiscreteActionOutputApplier(actionSpec, 2020, null);
var agentIds = new List <int> {
42, 1337
};
var actionBuffers = new Dictionary <int, ActionBuffers>();
actionBuffers[42] = new ActionBuffers(actionSpec);
actionBuffers[1337] = new ActionBuffers(actionSpec);
var actionTensor = new TensorProxy
{
data = new Tensor(
2,
2,
new[]
{
2.0f, // Agent 0, branch 0
1.0f, // Agent 0, branch 1
0.0f, // Agent 1, branch 0
0.0f // Agent 1, branch 1
}),
shape = new long[] { 2, 2 },
valueType = TensorProxy.TensorType.FloatingPoint
};
applier.Apply(actionTensor, agentIds, actionBuffers);
Assert.AreEqual(2, actionBuffers[42].DiscreteActions[0]);
Assert.AreEqual(1, actionBuffers[42].DiscreteActions[1]);
Assert.AreEqual(0, actionBuffers[1337].DiscreteActions[0]);
Assert.AreEqual(0, actionBuffers[1337].DiscreteActions[1]);
}
