| 2022-11-22 12:04:36 - r - INFO: - n_states: 6, n_actions: 3 | |
| 2022-11-22 12:04:39 - r - INFO: - Start training! | |
| 2022-11-22 12:04:39 - r - INFO: - Env: Acrobot-v1, Algorithm: DQN, Device: cuda | |
| 2022-11-22 12:04:39 - r - INFO: - Episode: 1/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:40 - r - INFO: - Episode: 2/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:40 - r - INFO: - Episode: 3/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:40 - r - INFO: - Episode: 4/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:41 - r - INFO: - Episode: 5/100, Reward: -189.000, Step: 190 | |
| 2022-11-22 12:04:41 - r - INFO: - Current episode 5 has the best eval reward: -200.000 | |
| 2022-11-22 12:04:42 - r - INFO: - Episode: 6/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:42 - r - INFO: - Episode: 7/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:42 - r - INFO: - Episode: 8/100, Reward: -132.000, Step: 133 | |
| 2022-11-22 12:04:43 - r - INFO: - Episode: 9/100, Reward: -101.000, Step: 102 | |
| 2022-11-22 12:04:43 - r - INFO: - Episode: 10/100, Reward: -148.000, Step: 149 | |
| 2022-11-22 12:04:44 - r - INFO: - Current episode 10 has the best eval reward: -200.000 | |
| 2022-11-22 12:04:44 - r - INFO: - Episode: 11/100, Reward: -188.000, Step: 189 | |
| 2022-11-22 12:04:44 - r - INFO: - Episode: 12/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:45 - r - INFO: - Episode: 13/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:45 - r - INFO: - Episode: 14/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:45 - r - INFO: - Episode: 15/100, Reward: -181.000, Step: 182 | |
| 2022-11-22 12:04:46 - r - INFO: - Current episode 15 has the best eval reward: -193.900 | |
| 2022-11-22 12:04:46 - r - INFO: - Episode: 16/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:47 - r - INFO: - Episode: 17/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:47 - r - INFO: - Episode: 18/100, Reward: -184.000, Step: 185 | |
| 2022-11-22 12:04:47 - r - INFO: - Episode: 19/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:48 - r - INFO: - Episode: 20/100, Reward: -180.000, Step: 181 | |
| 2022-11-22 12:04:48 - r - INFO: - Current episode 20 has the best eval reward: -151.000 | |
| 2022-11-22 12:04:49 - r - INFO: - Episode: 21/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:49 - r - INFO: - Episode: 22/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:49 - r - INFO: - Episode: 23/100, Reward: -139.000, Step: 140 | |
| 2022-11-22 12:04:50 - r - INFO: - Episode: 24/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:50 - r - INFO: - Episode: 25/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:51 - r - INFO: - Episode: 26/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:51 - r - INFO: - Episode: 27/100, Reward: -159.000, Step: 160 | |
| 2022-11-22 12:04:52 - r - INFO: - Episode: 28/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:52 - r - INFO: - Episode: 29/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:52 - r - INFO: - Episode: 30/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:53 - r - INFO: - Episode: 31/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:54 - r - INFO: - Episode: 32/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:54 - r - INFO: - Episode: 33/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:55 - r - INFO: - Episode: 34/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:55 - r - INFO: - Episode: 35/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:56 - r - INFO: - Episode: 36/100, Reward: -165.000, Step: 166 | |
| 2022-11-22 12:04:56 - r - INFO: - Episode: 37/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:57 - r - INFO: - Episode: 38/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:57 - r - INFO: - Episode: 39/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:57 - r - INFO: - Episode: 40/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:58 - r - INFO: - Current episode 40 has the best eval reward: -141.800 | |
| 2022-11-22 12:04:58 - r - INFO: - Episode: 41/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:58 - r - INFO: - Episode: 42/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:59 - r - INFO: - Episode: 43/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:04:59 - r - INFO: - Episode: 44/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:00 - r - INFO: - Episode: 45/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:01 - r - INFO: - Episode: 46/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:01 - r - INFO: - Episode: 47/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:01 - r - INFO: - Episode: 48/100, Reward: -186.000, Step: 187 | |
| 2022-11-22 12:05:02 - r - INFO: - Episode: 49/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:02 - r - INFO: - Episode: 50/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:03 - r - INFO: - Episode: 51/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:03 - r - INFO: - Episode: 52/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:04 - r - INFO: - Episode: 53/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:04 - r - INFO: - Episode: 54/100, Reward: -156.000, Step: 157 | |
| 2022-11-22 12:05:04 - r - INFO: - Episode: 55/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:05 - r - INFO: - Episode: 56/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:06 - r - INFO: - Episode: 57/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:06 - r - INFO: - Episode: 58/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:06 - r - INFO: - Episode: 59/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:07 - r - INFO: - Episode: 60/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:08 - r - INFO: - Episode: 61/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:08 - r - INFO: - Episode: 62/100, Reward: -191.000, Step: 192 | |
| 2022-11-22 12:05:08 - r - INFO: - Episode: 63/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:09 - r - INFO: - Episode: 64/100, Reward: -187.000, Step: 188 | |
| 2022-11-22 12:05:09 - r - INFO: - Episode: 65/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:10 - r - INFO: - Episode: 66/100, Reward: -158.000, Step: 159 | |
| 2022-11-22 12:05:10 - r - INFO: - Episode: 67/100, Reward: -164.000, Step: 165 | |
| 2022-11-22 12:05:11 - r - INFO: - Episode: 68/100, Reward: -134.000, Step: 135 | |
| 2022-11-22 12:05:11 - r - INFO: - Episode: 69/100, Reward: -200.000, Step: 200 | |
| 2022-11-22 12:05:11 - r - INFO: - Episode: 70/100, Reward: -144.000, Step: 145 | |
| 2022-11-22 12:05:12 - r - INFO: - Episode: 71/100, Reward: -193.000, Step: 194 | |
| 2022-11-22 12:05:13 - r - INFO: - Episode: 72/100, Reward: -137.000, Step: 138 | |
| 2022-11-22 12:05:13 - r - INFO: - Episode: 73/100, Reward: -183.000, Step: 184 | |
| 2022-11-22 12:05:13 - r - INFO: - Episode: 74/100, Reward: -141.000, Step: 142 | |
| 2022-11-22 12:05:14 - r - INFO: - Episode: 75/100, Reward: -163.000, Step: 164 | |
| 2022-11-22 12:05:14 - r - INFO: - Current episode 75 has the best eval reward: -93.500 | |
| 2022-11-22 12:05:14 - r - INFO: - Episode: 76/100, Reward: -71.000, Step: 72 | |
| 2022-11-22 12:05:14 - r - INFO: - Episode: 77/100, Reward: -71.000, Step: 72 | |
| 2022-11-22 12:05:14 - r - INFO: - Episode: 78/100, Reward: -154.000, Step: 155 | |
| 2022-11-22 12:05:15 - r - INFO: - Episode: 79/100, Reward: -117.000, Step: 118 | |
| 2022-11-22 12:05:15 - r - INFO: - Episode: 80/100, Reward: -175.000, Step: 176 | |
| 2022-11-22 12:05:16 - r - INFO: - Episode: 81/100, Reward: -187.000, Step: 188 | |
| 2022-11-22 12:05:16 - r - INFO: - Episode: 82/100, Reward: -111.000, Step: 112 | |
| 2022-11-22 12:05:16 - r - INFO: - Episode: 83/100, Reward: -86.000, Step: 87 | |
| 2022-11-22 12:05:16 - r - INFO: - Episode: 84/100, Reward: -85.000, Step: 86 | |
| 2022-11-22 12:05:17 - r - INFO: - Episode: 85/100, Reward: -93.000, Step: 94 | |
| 2022-11-22 12:05:17 - r - INFO: - Episode: 86/100, Reward: -131.000, Step: 132 | |
| 2022-11-22 12:05:18 - r - INFO: - Episode: 87/100, Reward: -128.000, Step: 129 | |
| 2022-11-22 12:05:18 - r - INFO: - Episode: 88/100, Reward: -194.000, Step: 195 | |
| 2022-11-22 12:05:18 - r - INFO: - Episode: 89/100, Reward: -93.000, Step: 94 | |
| 2022-11-22 12:05:18 - r - INFO: - Episode: 90/100, Reward: -91.000, Step: 92 | |
| 2022-11-22 12:05:19 - r - INFO: - Episode: 91/100, Reward: -161.000, Step: 162 | |
| 2022-11-22 12:05:19 - r - INFO: - Episode: 92/100, Reward: -103.000, Step: 104 | |
| 2022-11-22 12:05:19 - r - INFO: - Episode: 93/100, Reward: -110.000, Step: 111 | |
| 2022-11-22 12:05:20 - r - INFO: - Episode: 94/100, Reward: -191.000, Step: 192 | |
| 2022-11-22 12:05:20 - r - INFO: - Episode: 95/100, Reward: -70.000, Step: 71 | |
| 2022-11-22 12:05:20 - r - INFO: - Episode: 96/100, Reward: -71.000, Step: 72 | |
| 2022-11-22 12:05:21 - r - INFO: - Episode: 97/100, Reward: -125.000, Step: 126 | |
| 2022-11-22 12:05:21 - r - INFO: - Episode: 98/100, Reward: -109.000, Step: 110 | |
| 2022-11-22 12:05:21 - r - INFO: - Episode: 99/100, Reward: -104.000, Step: 105 | |
| 2022-11-22 12:05:21 - r - INFO: - Episode: 100/100, Reward: -93.000, Step: 94 | |
| 2022-11-22 12:05:22 - r - INFO: - Finish training! | |