axnedergaard / normalized-advantage-functions Goto Github PK

python3 experiment.py --environment MountainCarContinuous-v0 --learning_rate 0.01 --episodes 2000 --hidden_size 16 32 
200 --output results.txt
Traceback (most recent call last):
  File "experiment.py", line 10, in <module>
    import naf
  File "/Users/Victor/continuous-deep-q-learning/naf.py", line 16, in <module>
    from tensorflow.python.ops.distributions.util import fill_lower_triangular
ModuleNotFoundError: No module named 'tensorflow.python.ops.distributions'

@@ -13,7 +13,21 @@
 import tensorflow as tf
 import numpy as np
 import random
-from tensorflow.python.ops.distributions.util import fill_lower_triangular
+# from tensorflow.python.ops.distributions.util import fill_lower_triangular
+
+def fill_lower_triangular(x):
+    """
+    Numpy implementation of `fill_lower_triangular`.
+        Dumped from https://programtalk.com/vs2/python/13142/deep_recommend_system/java_predict_client/src/main/proto/tensorflow/contrib/distributions/python/kernel_tests/distribution_util_test.py/
+    """
+    x = np.asarray(x)
+    d = x.shape[-1]
+    # d = n(n+1)/2 implies n is:
+    n = int(0.5 * (math.sqrt(1. + 8. * d) - 1.))
+    ids = np.tril_indices(n)
+    y = np.zeros(list(x.shape[:-1]) + [n, n], dtype=x.dtype)
+    y[..., ids[0], ids[1]] = x
+    return y

python3 experiment.py --environment MountainCarContinuous-v0 --learning_rate 0.01 --episodes 2000 --hidden_size 16 32 
200 --output results.txt
[2017-12-19 18:13:39,003] Making new env: MountainCarContinuous-v0
Traceback (most recent call last):
  File "experiment.py", line 149, in <module>
    rewards = recursive_experiment(keys, vals, [])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 67, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:],  vals + [r])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  [Previous line repeated 1 more times]
  File "experiment.py", line 67, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:],  vals + [r])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 67, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:],  vals + [r])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  File "experiment.py", line 64, in recursive_experiment
    rewards += recursive_experiment(keys, remaining_vals[1:], vals + [remaining_vals[0]])
  [Previous line repeated 3 more times]
  File "experiment.py", line 60, in recursive_experiment
    return [experiment(dict(zip(keys,vals)))]
  File "experiment.py", line 78, in experiment
    agent = naf.Agent(args['v'], env.observation_space, env.action_space, args['learning_rate'], args['batch_normalize'], args['gamma'], args['tau'], args['epsilon'], args['hidden_size'], args['hidden_n'], args['hidden_activation'], args['batch_size'], args['memory_capacity'], args['load_path'], args['covariance'])
  File "/Users/Victor/continuous-deep-q-learning/naf.py", line 144, in __init__
    self.N = fill_lower_triangular(self.M.h)
  File "/Users/Victor/continuous-deep-q-learning/naf.py", line 24, in fill_lower_triangular
    d = x.shape[-1]
IndexError: tuple index out of range