Starting time: Thu, 07 Sep 2017 22:11:24 Episode 0 reward (training): 0.77 Episode 5 reward (training): 0.66 Episode 10 reward (training): 1.27 episode: 10 Evaluation(testing) Average Return: 0.249565513532 Episode 15 reward (training): 0.29 episode: 20 Evaluation(testing) Average Return: 0.282877010907 Episode 20 reward (training): 0.21 Episode 25 reward (training): 1.01 Episode 30 reward (training): -0.01 episode: 30 Evaluation(testing) Average Return: 0.275043940261 Episode 35 reward (training): 1.52 Episode 40 reward (training): -0.75 Episode 45 reward (training): 1.31 episode: 40 Evaluation(testing) Average Return: 0.258638034099 Episode 50 reward (training): 0.80 episode: 50 Evaluation(testing) Average Return: 0.252977419324 Episode 55 reward (training): 1.07 Episode 60 reward (training): 0.50 Episode 65 reward (training): -0.79 episode: 60 Evaluation(testing) Average Return: -0.803841265937 Episode 70 reward (training): -0.80 Episode 75 reward (training): 0.88 episode: 70 Evaluation(testing) Average Return: -0.692373570603 Episode 80 reward (training): -0.72 episode: 80 Evaluation(testing) Average Return: -0.865256179297 Episode 85 reward (training): 1.39