Logging to logs/HalfCheetah-v3/exp-1/maxentirl/2023_11_09_05_40_02
--2023-11-09 05:41:14.021603 CST--
| Itration            | 0        |
| Real Det Return     | 1.75e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.77e+03 |
| Real Sto violation  | 0.85     |
| Reward Loss         | -127     |
| Running Env Steps   | 0        |
| Running Forward KL  | 17.1     |
| Running Reverse KL  | 10.6     |
| Running Update Time | 0        |
----------------------------------
--2023-11-09 05:42:35.897007 CST--
| Itration            | 1        |
| Real Det Return     | 1.75e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.81e+03 |
| Real Sto violation  | 0.4      |
| Reward Loss         | -56.6    |
| Running Env Steps   | 5000     |
| Running Forward KL  | 15.9     |
| Running Reverse KL  | 11.3     |
| Running Update Time | 1        |
----------------------------------
--2023-11-09 05:43:58.040035 CST--
| Itration            | 2        |
| Real Det Return     | 1.75e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.83e+03 |
| Real Sto violation  | 0.7      |
| Reward Loss         | -66.3    |
| Running Env Steps   | 10000    |
| Running Forward KL  | 15.5     |
| Running Reverse KL  | 11.1     |
| Running Update Time | 2        |
----------------------------------
--2023-11-09 05:45:20.774261 CST--
| Itration            | 3        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.86e+03 |
| Real Sto violation  | 0.25     |
| Reward Loss         | -58.4    |
| Running Env Steps   | 15000    |
| Running Forward KL  | 14.9     |
| Running Reverse KL  | 11.4     |
| Running Update Time | 3        |
----------------------------------
--2023-11-09 05:46:43.164212 CST--
| Itration            | 4        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.88e+03 |
| Real Sto violation  | 0.1      |
| Reward Loss         | -58.6    |
| Running Env Steps   | 20000    |
| Running Forward KL  | 13.9     |
| Running Reverse KL  | 11.7     |
| Running Update Time | 4        |
----------------------------------
--2023-11-09 05:48:05.433342 CST--
| Itration            | 5        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.89e+03 |
| Real Sto violation  | 0.1      |
| Reward Loss         | -70.9    |
| Running Env Steps   | 25000    |
| Running Forward KL  | 13.3     |
| Running Reverse KL  | 12       |
| Running Update Time | 5        |
----------------------------------
--2023-11-09 05:49:27.689230 CST--
| Itration            | 6        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.89e+03 |
| Real Sto violation  | 0.2      |
| Reward Loss         | -84.8    |
| Running Env Steps   | 30000    |
| Running Forward KL  | 13.9     |
| Running Reverse KL  | 11.9     |
| Running Update Time | 6        |
----------------------------------
--2023-11-09 05:50:49.875478 CST--
| Itration            | 7        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.9e+03  |
| Real Sto violation  | 0.15     |
| Reward Loss         | -98.5    |
| Running Env Steps   | 35000    |
| Running Forward KL  | 13.3     |
| Running Reverse KL  | 11.7     |
| Running Update Time | 7        |
----------------------------------
--2023-11-09 05:52:12.872661 CST--
| Itration            | 8        |
| Real Det Return     | 1.75e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.89e+03 |
| Real Sto violation  | 0.05     |
| Reward Loss         | -109     |
| Running Env Steps   | 40000    |
| Running Forward KL  | 13.4     |
| Running Reverse KL  | 12       |
| Running Update Time | 8        |
----------------------------------
--2023-11-09 05:53:35.786162 CST--
| Itration            | 9        |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.89e+03 |
| Real Sto violation  | 0.1      |
| Reward Loss         | -127     |
| Running Env Steps   | 45000    |
| Running Forward KL  | 13.7     |
| Running Reverse KL  | 11.9     |
| Running Update Time | 9        |
----------------------------------
--2023-11-09 05:54:59.074246 CST--
| Itration            | 10       |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.9e+03  |
| Real Sto violation  | 0.15     |
| Reward Loss         | -140     |
| Running Env Steps   | 50000    |
| Running Forward KL  | 13.8     |
| Running Reverse KL  | 11.9     |
| Running Update Time | 10       |
----------------------------------
--2023-11-09 05:56:24.034336 CST--
| Itration            | 11       |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.89e+03 |
| Real Sto violation  | 0.15     |
| Reward Loss         | -154     |
| Running Env Steps   | 55000    |
| Running Forward KL  | 14       |
| Running Reverse KL  | 11.6     |
| Running Update Time | 11       |
----------------------------------
--2023-11-09 05:57:50.104897 CST--
| Itration            | 12       |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.92e+03 |
| Real Sto violation  | 0.2      |
| Reward Loss         | -166     |
| Running Env Steps   | 60000    |
| Running Forward KL  | 13.2     |
| Running Reverse KL  | 11.7     |
| Running Update Time | 12       |
----------------------------------
--2023-11-09 05:59:17.638884 CST--
| Itration            | 13       |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.92e+03 |
| Real Sto violation  | 0.1      |
| Reward Loss         | -177     |
| Running Env Steps   | 65000    |
| Running Forward KL  | 13.2     |
| Running Reverse KL  | 11.6     |
| Running Update Time | 13       |
----------------------------------
--2023-11-09 06:00:49.782419 CST--
| Itration            | 14       |
| Real Det Return     | 1.76e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | 1.92e+03 |
| Real Sto violation  | 0.15     |
| Reward Loss         | -190     |
| Running Env Steps   | 70000    |
| Running Forward KL  | 13.7     |
| Running Reverse KL  | 11.5     |
| Running Update Time | 14       |
----------------------------------
