policy,episode,total_reward,final_fairness,final_utility,steps,early_submits_blocked baseline,1,0.5462,0.0383,0.532,12,0 baseline,2,0.5514,0.1166,0.5632,12,0 baseline,3,0.5435,-0.024,0.507,12,0 baseline,4,0.5501,0.1133,0.562,12,0 baseline,5,0.5477,0.0458,0.535,12,0 baseline,6,0.5519,0.1353,0.5708,12,0 baseline,7,0.5489,0.061,0.541,12,0 baseline,8,0.5508,0.114,0.5622,12,0 baseline,9,0.5499,0.0883,0.552,12,0 baseline,10,0.5486,0.0708,0.545,12,0 baseline,11,0.5491,0.0738,0.5462,12,0 baseline,12,0.5483,0.0883,0.552,12,0 baseline,13,0.5501,0.0853,0.5508,12,0 baseline,14,0.5452,0.0151,0.5228,12,0 baseline,15,0.5494,0.0883,0.552,12,0 baseline,16,0.5518,0.1166,0.5632,12,0 baseline,17,0.5444,0.0133,0.522,12,0 baseline,18,0.5478,0.0633,0.542,12,0 baseline,19,0.5478,0.0708,0.545,12,0 baseline,20,0.5457,0.0103,0.5208,12,0 baseline,21,0.5515,0.1383,0.572,12,0 baseline,22,0.551,0.1133,0.562,12,0 baseline,23,0.5479,0.0595,0.5404,12,0 baseline,24,0.5465,0.0383,0.532,12,0 baseline,25,0.5507,0.0916,0.5532,12,0 baseline,26,0.5497,0.0958,0.555,12,0 baseline,27,0.5498,0.0853,0.5508,12,0 baseline,28,0.5496,0.086,0.551,12,0 baseline,29,0.5478,0.0565,0.5392,12,0 baseline,30,0.5483,0.0883,0.552,12,0 baseline,31,0.5524,0.1383,0.572,12,0 baseline,32,0.5459,0.0178,0.5238,12,0 trained,1,0.6023,0.056,0.539,12,0 trained,2,0.6028,0.0853,0.5508,12,0 trained,3,0.6023,0.056,0.539,12,0 trained,4,0.6021,0.056,0.539,12,0 trained,5,0.6005,0.0633,0.542,12,0 trained,6,0.6041,0.1123,0.5616,12,0 trained,7,0.6053,0.1383,0.572,12,0 trained,8,0.5985,0.026,0.527,12,0 trained,9,0.6018,0.0603,0.5408,12,0 trained,10,0.6014,0.0633,0.542,12,0 trained,11,0.5983,0.0029,0.5178,12,0 trained,12,0.6033,0.0883,0.552,12,0 trained,13,0.6046,0.1133,0.562,12,0 trained,14,0.6028,0.0883,0.552,12,0 trained,15,0.6057,0.1383,0.572,12,0 trained,16,0.5986,0.029,0.5282,12,0 trained,17,0.6057,0.1383,0.572,12,0 trained,18,0.6034,0.0832,0.55,12,0 trained,19,0.6028,0.0883,0.552,12,0 trained,20,0.6049,0.1353,0.5708,12,0 trained,21,0.6064,0.1633,0.582,12,0 trained,22,0.5984,0.029,0.5282,12,0 trained,23,0.603,0.081,0.549,12,0 trained,24,0.6029,0.0853,0.5508,12,0 trained,25,0.6015,0.0603,0.5408,12,0 trained,26,0.6053,0.1373,0.5716,12,0 trained,27,0.6004,0.029,0.5282,12,0 trained,28,0.6002,0.029,0.5282,12,0 trained,29,0.6035,0.1133,0.562,12,0 trained,30,0.6011,0.054,0.5382,12,0 trained,31,0.5999,0.0353,0.5308,12,0 trained,32,0.6027,0.0873,0.5516,12,0