11

dqn.py

@@ -0,0 +1,25 @@
+import numpy as np
+import torch
+
+
+def dev0(a, b):
+    a = a.detach().numpy()
+    b = b.detach().numpy()
+    with np.errstate(divide='ignore', invalid='ignore'):
+        c = np.true_divide(a, b)
+        c[~ np.isfinite(c)] = 0
+    c = torch.from_numpy(c)
+    return c
+
+
+def soft_update(target, source, tau):
+    for target_param, param in zip(target.parameters(), source.parameters()):
+        target_param.data.copy_(target_param.data * (1.0 - tau) + param.data * tau)
+
+
+def hard_update(target, source):
+    for target_param, param in zip(target.parameters(), source.parameters()):
+        target_param.data.copy_(param.data)
+
+
+class DeepQNetwork: