2022-11-22 21:53:05 - r - INFO: - n_states: 13, n_actions: 4 2022-11-22 21:53:05 - r - INFO: - Start training! 2022-11-22 21:53:05 - r - INFO: - Env: theAlley, Algorithm: VI, Device: cpu 2022-11-22 21:53:05 - r - INFO: - Episode: 1/100, Reward: 10.000, Step: 27 2022-11-22 21:53:05 - r - INFO: - Episode: 2/100, Reward: -5.000, Step: 11 2022-11-22 21:53:05 - r - INFO: - Episode: 3/100, Reward: -5.000, Step: 12 2022-11-22 21:53:05 - r - INFO: - Episode: 4/100, Reward: -5.000, Step: 8 2022-11-22 21:53:05 - r - INFO: - Episode: 5/100, Reward: 10.000, Step: 18 2022-11-22 21:53:05 - r - INFO: - Current episode 5 has the best eval reward: 4.000 2022-11-22 21:53:06 - r - INFO: - Episode: 6/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 7/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 8/100, Reward: -5.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 9/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 10/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 11/100, Reward: 10.000, Step: 17 2022-11-22 21:53:06 - r - INFO: - Episode: 12/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 13/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 14/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 15/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Current episode 15 has the best eval reward: 5.500 2022-11-22 21:53:06 - r - INFO: - Episode: 16/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 17/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 18/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 19/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 20/100, Reward: 10.000, Step: 17 2022-11-22 21:53:06 - r - INFO: - Current episode 20 has the best eval reward: 5.500 2022-11-22 21:53:06 - r - INFO: - Episode: 21/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 22/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 23/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 24/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 25/100, Reward: -5.000, Step: 9 2022-11-22 21:53:06 - r - INFO: - Current episode 25 has the best eval reward: 8.500 2022-11-22 21:53:06 - r - INFO: - Episode: 26/100, Reward: -5.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 27/100, Reward: -5.000, Step: 10 2022-11-22 21:53:06 - r - INFO: - Episode: 28/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 29/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 30/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 31/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 32/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 33/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 34/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 35/100, Reward: -5.000, Step: 8 2022-11-22 21:53:06 - r - INFO: - Episode: 36/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 37/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 38/100, Reward: -5.000, Step: 8 2022-11-22 21:53:06 - r - INFO: - Episode: 39/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 40/100, Reward: -5.000, Step: 6 2022-11-22 21:53:06 - r - INFO: - Episode: 41/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 42/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 43/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 44/100, Reward: 10.000, Step: 17 2022-11-22 21:53:06 - r - INFO: - Episode: 45/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 46/100, Reward: -5.000, Step: 8 2022-11-22 21:53:06 - r - INFO: - Episode: 47/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 48/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 49/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 50/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 51/100, Reward: -5.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 52/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 53/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 54/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 55/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 56/100, Reward: -5.000, Step: 9 2022-11-22 21:53:06 - r - INFO: - Episode: 57/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 58/100, Reward: -5.000, Step: 10 2022-11-22 21:53:06 - r - INFO: - Episode: 59/100, Reward: 10.000, Step: 19 2022-11-22 21:53:06 - r - INFO: - Episode: 60/100, Reward: -5.000, Step: 6 2022-11-22 21:53:06 - r - INFO: - Episode: 61/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 62/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 63/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 64/100, Reward: 10.000, Step: 20 2022-11-22 21:53:06 - r - INFO: - Episode: 65/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 66/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 67/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 68/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 69/100, Reward: -5.000, Step: 7 2022-11-22 21:53:06 - r - INFO: - Episode: 70/100, Reward: -5.000, Step: 11 2022-11-22 21:53:06 - r - INFO: - Episode: 71/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 72/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 73/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 74/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 75/100, Reward: -5.000, Step: 9 2022-11-22 21:53:06 - r - INFO: - Episode: 76/100, Reward: -5.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 77/100, Reward: -5.000, Step: 10 2022-11-22 21:53:06 - r - INFO: - Episode: 78/100, Reward: 10.000, Step: 19 2022-11-22 21:53:06 - r - INFO: - Episode: 79/100, Reward: 10.000, Step: 17 2022-11-22 21:53:06 - r - INFO: - Episode: 80/100, Reward: 10.000, Step: 19 2022-11-22 21:53:06 - r - INFO: - Episode: 81/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 82/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 83/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 84/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 85/100, Reward: -5.000, Step: 9 2022-11-22 21:53:06 - r - INFO: - Episode: 86/100, Reward: 10.000, Step: 18 2022-11-22 21:53:06 - r - INFO: - Episode: 87/100, Reward: -5.000, Step: 6 2022-11-22 21:53:06 - r - INFO: - Episode: 88/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 89/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 90/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 91/100, Reward: 10.000, Step: 15 2022-11-22 21:53:06 - r - INFO: - Episode: 92/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 93/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Episode: 94/100, Reward: 10.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 95/100, Reward: 10.000, Step: 16 2022-11-22 21:53:06 - r - INFO: - Episode: 96/100, Reward: -5.000, Step: 5 2022-11-22 21:53:06 - r - INFO: - Episode: 97/100, Reward: -5.000, Step: 6 2022-11-22 21:53:06 - r - INFO: - Episode: 98/100, Reward: -5.000, Step: 13 2022-11-22 21:53:06 - r - INFO: - Episode: 99/100, Reward: 10.000, Step: 12 2022-11-22 21:53:06 - r - INFO: - Episode: 100/100, Reward: 10.000, Step: 14 2022-11-22 21:53:06 - r - INFO: - Finish training!