feat(PPO_Bot): full PPO RL implementation (#14, #15, #16, #17)

spike/arraymancer-test/arraymancer_test.nimble

@@ -0,0 +1,9 @@
+# Package
+version = "0.1.0"
+author = "SirStone"
+description = "Arraymancer viability spike — XOR perceptron"
+license = "MIT"
+
+# Dependencies
+requires "nim >= 2.0.0"
+requires "arraymancer >= 0.7.0"

spike/arraymancer-test/test_xor.nim

@@ -0,0 +1,63 @@
+import arraymancer
+import std/[strformat, times]
+
+# XOR dataset — [4,2] inputs, [4,1] targets
+let xData = [[0.0'f32, 0.0'f32],
+             [0.0'f32, 1.0'f32],
+             [1.0'f32, 0.0'f32],
+             [1.0'f32, 1.0'f32]].toTensor()
+
+let yData = [[0.0'f32], [1.0'f32], [1.0'f32], [0.0'f32]].toTensor()
+
+var ctx = newContext Tensor[float32]
+
+let l1 = ctx.init(Linear[float32], 2, 4)
+let l2 = ctx.init(Linear[float32], 4, 1)
+
+type XorNet = object
+  l1: Linear[float32]
+  l2: Linear[float32]
+
+var net = XorNet(l1: l1, l2: l2)
+var adam = optimizer(net, Adam, learning_rate = 0.01'f32)
+
+let t0 = cpuTime()
+
+for epoch in 1..1000:
+  let xVar = ctx.variable(xData)
+  let yVar = ctx.variable(yData)
+
+  # Forward
+  let h    = l1.forward(xVar).sigmoid()
+  let pred = l2.forward(h).sigmoid()
+
+  # MSE loss: mean((pred - y)^2)
+  let diff = pred - yVar
+  let loss = mean(diff *. diff)
+
+  if epoch mod 200 == 0:
+    echo &"Epoch {epoch:4d}  loss = {loss.value[0]:.6f}"
+
+  loss.backprop()
+  adam.update()
+
+let trainTime = cpuTime() - t0
+
+# Inference (no grad)
+echo ""
+echo "Final predictions:"
+let xVar  = ctx.variable(xData)
+let hInf  = l1.forward(xVar).sigmoid()
+let preds = l2.forward(hInf).sigmoid()
+
+var allCorrect = true
+for i in 0..<4:
+  let p       = preds.value[i, 0]
+  let rounded = if p >= 0.5'f32: 1 else: 0
+  let expected = [0,1,1,0][i]
+  if rounded != expected: allCorrect = false
+  echo &"  [{xData[i,0].int},{xData[i,1].int}] -> {p:.4f}  (rounded: {rounded}, expected: {expected})"
+
+echo ""
+echo &"All correct: {allCorrect}"
+echo &"Training time: {trainTime:.2f}s"