| step,critic_loss,actor_loss,bc_loss,q_value_mean,q_value_std | |
| 10000,0.008186,-2.839091,0.152631,0.980354,0.064071 | |
| 20000,0.009554,-2.620792,0.043287,1.156570,0.061793 | |
| 30000,0.006662,-2.595127,0.030103,1.031939,0.069421 | |
| 40000,0.005977,-2.580591,0.028780,0.978247,0.046694 | |
| 50000,0.006652,-2.676886,0.056827,1.071500,0.079495 | |
| 60000,0.011545,-2.744316,0.078478,1.423170,0.207973 | |
| 70000,0.018581,-2.852649,0.071268,1.857630,0.239949 | |
| 80000,0.014791,-2.723853,0.044637,1.644105,0.232435 | |
| 90000,0.017475,-2.811121,0.075968,1.789109,0.250880 | |
| 100000,0.024209,-2.741790,0.047254,1.899313,0.205460 | |