Using cuda device
Wrapping the env with a `Monitor` wrapper
Wrapping the env in a DummyVecEnv.
Logging to complexcity_dqn/DQN_1
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 93.8      |
|    ep_rew_mean      | -2.42e+03 |
|    exploration_rate | 0.644     |
| time/               |           |
|    episodes         | 4         |
|    fps              | 19        |
|    time_elapsed     | 18        |
|    total_timesteps  | 375       |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 28.7      |
|    n_updates        | 174       |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 82        |
|    ep_rew_mean      | -2.32e+03 |
|    exploration_rate | 0.377     |
| time/               |           |
|    episodes         | 8         |
|    fps              | 22        |
|    time_elapsed     | 29        |
|    total_timesteps  | 656       |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 23        |
|    n_updates        | 455       |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 78.6      |
|    ep_rew_mean      | -2.48e+03 |
|    exploration_rate | 0.104     |
| time/               |           |
|    episodes         | 12        |
|    fps              | 23        |
|    time_elapsed     | 39        |
|    total_timesteps  | 943       |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 15.2      |
|    n_updates        | 742       |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 100       |
|    ep_rew_mean      | -2.71e+03 |
|    exploration_rate | 0.05      |
| time/               |           |
|    episodes         | 16        |
|    fps              | 25        |
|    time_elapsed     | 63        |
|    total_timesteps  | 1608      |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 13.5      |
|    n_updates        | 1407      |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 118       |
|    ep_rew_mean      | -3.24e+03 |
|    exploration_rate | 0.05      |
| time/               |           |
|    episodes         | 20        |
|    fps              | 25        |
|    time_elapsed     | 91        |
|    total_timesteps  | 2358      |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 9.51      |
|    n_updates        | 2157      |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 167       |
|    ep_rew_mean      | -3.79e+03 |
|    exploration_rate | 0.05      |
| time/               |           |
|    episodes         | 24        |
|    fps              | 26        |
|    time_elapsed     | 152       |
|    total_timesteps  | 4017      |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 10.4      |
|    n_updates        | 3816      |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 270       |
|    ep_rew_mean      | -1.26e+03 |
|    exploration_rate | 0.05      |
| time/               |           |
|    episodes         | 28        |
|    fps              | 26        |
|    time_elapsed     | 280       |
|    total_timesteps  | 7554      |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 17.4      |
|    n_updates        | 7353      |
-----------------------------------
-----------------------------------
| rollout/            |           |
|    ep_len_mean      | 285       |
|    ep_rew_mean      | -1.46e+03 |
|    exploration_rate | 0.05      |
| time/               |           |
|    episodes         | 32        |
|    fps              | 27        |
|    time_elapsed     | 334       |
|    total_timesteps  | 9134      |
| train/              |           |
|    learning_rate    | 0.0005    |
|    loss             | 28.6      |
|    n_updates        | 8933      |
-----------------------------------
 100% ━━━━━━━━━━━━━━━━━━━━━━━━━━━ 10,000/10,000  [ 0:06:03 < 0:00:00 , 29 it/s ]

Done Learning!!

1
