"C:\Program Files\Python36\python.exe" "C:/Users/woods/PycharmProjects/Gym/pg-pong py3.py" 0 C:/Users/woods/PycharmProjects/Gym/pg-pong py3.py:126: RuntimeWarning: invalid value encountered in true_divide discounted_epr /= np.std(discounted_epr) Resetting env. Episode reward total was -21.0. Running mean: -21.0 1 dict_items([('W1', array([[ 0.00036615, 0.00371536, -0.00239665, ..., -0.02003761, -0.04027144, 0.00205455], [ 0.02066932, 0.0180365 , 0.01907392, ..., 0.01545524, -0.00756541, -0.00646326], [-0.00887905, -0.0010941 , -0.00937016, ..., -0.01339622, -0.01115785, -0.00696481], ..., [ 0.0066034 , 0.01702268, -0.02974029, ..., 0.0024119 , -0.0001717 , -0.01751522], [ 0.0049871 , 0.00956012, -0.00614029, ..., -0.00938476, -0.00354607, -0.00254821], [ 0.00242294, -0.00281569, -0.00118415, ..., 0.00993396, -0.01041356, -0.01702613]])), ('W2', array([-1.09460922e-02, 6.95467592e-02, -9.10282447e-02, 1.11640908e-02, -3.16543127e-02, 1.45899356e-02, 5.72547714e-02, -5.49097768e-02, -3.59311322e-02, -6.08563812e-02, 5.64580306e-02, 1.23313977e-01, -2.99701618e-02, 3.45020927e-02, 2.55757738e-03, -1.28637064e-01, 3.78288421e-03, -6.46980365e-02, -1.85031633e-01, -5.81157510e-02, -4.64511449e-02, 2.84513700e-02, -5.27912336e-02, 2.43235338e-01, 1.08845140e-02, 1.44614812e-01, -6.93965121e-03, -1.10618008e-01, 1.31015128e-03, 9.37742311e-02, 3.71069407e-02, 1.35450017e-01, -3.55127860e-02, -2.81729794e-02, -2.31913159e-02, 1.01282755e-02, 1.03620505e-02, 7.07213989e-02, -8.36825983e-02, -3.89278335e-03, -7.78011283e-03, -2.15608054e-04, 8.41381975e-02, 1.08334383e-01, -1.05931564e-01, -5.14935515e-02, 8.13207244e-03, -9.18029807e-02, -4.73864330e-02, 9.63827045e-02, 1.21381761e-01, 1.65062554e-02, -8.34662430e-03, 3.48228617e-02, -1.37957103e-01, 1.02496874e-01, 6.80483236e-02, -4.56679480e-02, -3.64470650e-02, -8.25538291e-02, -4.32985162e-04, 3.80214448e-02, 2.22432598e-02, -3.52767312e-02, 8.05357161e-02, -7.23678195e-02, 9.36328389e-02, 1.09637273e-01, 1.49729928e-01, -3.69413554e-02, -1.45699614e-02, -1.01638521e-01, -3.27028110e-02, 7.07106926e-02, -5.84520304e-02, 4.65548815e-02, 4.54471503e-02, -9.14273254e-02, -1.35065077e-01, -6.35483815e-03, 3.33943372e-02, -2.45206159e-02, -2.11135182e-02, 4.92444986e-02, 3.63925851e-02, -1.43188260e-01, -3.78401624e-02, 1.06102730e-02, -3.16978909e-02, 1.51765712e-02, 2.52927451e-02, -7.78092339e-02, 6.25911041e-02, 1.02182610e-01, 4.74041904e-02, 7.53796197e-02, 4.45635678e-02, 5.31901623e-02, -1.68997401e-01, -9.04875680e-02, 2.67740775e-03, -1.22811695e-01, -1.78787821e-02, 8.40594505e-02, 1.29571722e-01, -1.01093176e-01, 3.94738351e-02, -4.66188145e-02, -9.82220182e-03, 1.39331697e-02, -4.88236901e-02, -8.15100668e-02, 3.38538000e-02, 1.25736766e-02, -2.79921070e-02, -2.11555356e-02, -3.59036172e-02, 3.85854584e-02, -2.82616263e-02, 4.24982051e-02, 3.85779562e-02, -1.76807519e-02, -1.18079732e-02, 2.86477740e-02, -4.96511783e-02, 2.19463165e-02, 2.91018643e-03, 9.02489584e-02, 2.69743525e-02, -1.36038788e-02, -1.44285646e-02, -4.18226207e-02, 2.05969592e-02, 1.14247413e-02, -1.28661858e-02, 5.21891240e-02, 1.53598586e-02, 1.53605855e-02, 1.73034003e-02, -3.92347212e-02, 3.27649321e-02, 7.20991585e-02, 4.89348275e-02, 8.75303858e-02, -3.66078560e-02, 2.54520657e-02, 9.78276697e-02, 8.46731850e-02, 1.60844354e-01, 7.84044922e-02, -1.06606018e-01, -3.51651690e-02, 5.07174433e-02, 3.04221709e-02, 8.15123645e-02, -7.42442516e-02, -1.62811884e-02, 9.27485009e-02, -2.87091028e-03, -1.07073350e-01, -3.95359838e-02, -5.54300099e-02, -3.97315580e-02, 5.29128244e-02, 3.65384393e-02, -1.96036292e-02, -4.89860758e-02, 1.73849850e-02, -9.74061247e-02, 3.26870401e-02, -4.32441445e-02, 1.28850502e-01, 6.77918632e-02, -3.93710914e-02, 5.47044000e-02, 1.76805684e-02, 1.04565333e-01, 2.41277395e-03, 3.39436800e-03, 5.59104170e-03, -2.96559432e-02, -5.19018882e-02, -1.80800274e-02, 4.55221474e-02, 6.40229069e-02, -2.16796636e-02, 8.51969135e-02, -5.24904109e-04, 3.73439298e-02, -1.04443755e-01, 8.45546338e-02, 3.44716515e-02, -1.82234005e-02, -5.91885442e-02, -4.21943980e-02, 9.00573696e-02, 6.92108280e-03, 4.61365289e-02, 9.24869941e-02, -2.17672047e-02]))]) Resetting env. Episode reward total was -20.0. Running mean: -20.99 C:/Users/woods/PycharmProjects/Gym/pg-pong py3.py:61: RuntimeWarning: invalid value encountered in less h[h < 0] = 0 # apply ReLU 2 C:/Users/woods/PycharmProjects/Gym/pg-pong py3.py:71: RuntimeWarning: invalid value encountered in less_equal dh[eph <= 0] = 0 # ReLU for back prop Resetting env. Episode reward total was -21.0. Running mean: -20.990099999999998 3 dict_items([('W1', array([[nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], ..., [nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan], [nan, nan, nan, ..., nan, nan, nan]])), ('W2', array([nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan]))]) Resetting env. Episode reward total was -21.0. Running mean: -20.990199 4 Resetting env. Episode reward total was -21.0. Running mean: -20.990297010000003 Process finished with exit code -1