Logging to logs/HalfCheetah-v3/exp-1/maxentirl_sa/2023_11_08_23_02_44
--2023-11-08 23:04:08.559100 CST--
| Itration            | 0        |
| Real Det Return     | -636     |
| Real Det violation  | 0.25     |
| Real Sto Return     | -162     |
| Real Sto violation  | 1        |
| Reward Loss         | 788      |
| Running Env Steps   | 0        |
| Running Forward KL  | 17.5     |
| Running Reverse KL  | 11.3     |
| Running Update Time | 0        |
----------------------------------
--2023-11-08 23:05:42.592450 CST---
| Itration            | 1         |
| Real Det Return     | -1.14e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -243      |
| Real Sto violation  | 1         |
| Reward Loss         | 793       |
| Running Env Steps   | 5000      |
| Running Forward KL  | 18.6      |
| Running Reverse KL  | 12.1      |
| Running Update Time | 1         |
-----------------------------------
--2023-11-08 23:07:08.472675 CST---
| Itration            | 2         |
| Real Det Return     | -1.51e+03 |
| Real Det violation  | 0.6       |
| Real Sto Return     | -321      |
| Real Sto violation  | 1         |
| Reward Loss         | 829       |
| Running Env Steps   | 10000     |
| Running Forward KL  | 18.3      |
| Running Reverse KL  | 12.6      |
| Running Update Time | 2         |
-----------------------------------
--2023-11-08 23:08:34.380100 CST---
| Itration            | 3         |
| Real Det Return     | -1.23e+03 |
| Real Det violation  | 0.4       |
| Real Sto Return     | -327      |
| Real Sto violation  | 1         |
| Reward Loss         | 808       |
| Running Env Steps   | 15000     |
| Running Forward KL  | 19.1      |
| Running Reverse KL  | 12.5      |
| Running Update Time | 3         |
-----------------------------------
--2023-11-08 23:09:57.772430 CST---
| Itration            | 4         |
| Real Det Return     | -1.66e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -331      |
| Real Sto violation  | 1         |
| Reward Loss         | 725       |
| Running Env Steps   | 20000     |
| Running Forward KL  | 19.5      |
| Running Reverse KL  | 11.6      |
| Running Update Time | 4         |
-----------------------------------
--2023-11-08 23:11:23.937962 CST---
| Itration            | 5         |
| Real Det Return     | -1.61e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -426      |
| Real Sto violation  | 1         |
| Reward Loss         | 680       |
| Running Env Steps   | 25000     |
| Running Forward KL  | 18.7      |
| Running Reverse KL  | 12        |
| Running Update Time | 5         |
-----------------------------------
--2023-11-08 23:12:49.863650 CST---
| Itration            | 6         |
| Real Det Return     | -1.51e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -386      |
| Real Sto violation  | 1         |
| Reward Loss         | 600       |
| Running Env Steps   | 30000     |
| Running Forward KL  | 18.6      |
| Running Reverse KL  | 11        |
| Running Update Time | 6         |
-----------------------------------
--2023-11-08 23:14:15.704794 CST--
| Itration            | 7        |
| Real Det Return     | -1.6e+03 |
| Real Det violation  | 0        |
| Real Sto Return     | -426     |
| Real Sto violation  | 1        |
| Reward Loss         | 610      |
| Running Env Steps   | 35000    |
| Running Forward KL  | 18.2     |
| Running Reverse KL  | 11       |
| Running Update Time | 7        |
----------------------------------
--2023-11-08 23:15:43.700808 CST---
| Itration            | 8         |
| Real Det Return     | -1.53e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -434      |
| Real Sto violation  | 1         |
| Reward Loss         | 594       |
| Running Env Steps   | 40000     |
| Running Forward KL  | 18.6      |
| Running Reverse KL  | 11.5      |
| Running Update Time | 8         |
-----------------------------------
--2023-11-08 23:17:15.339740 CST---
| Itration            | 9         |
| Real Det Return     | -1.49e+03 |
| Real Det violation  | 0         |
| Real Sto Return     | -393      |
| Real Sto violation  | 1         |
| Reward Loss         | 572       |
| Running Env Steps   | 45000     |
| Running Forward KL  | 18.5      |
| Running Reverse KL  | 11        |
| Running Update Time | 9         |
-----------------------------------
