| evaluation/total.timesteps,evaluation/episode.final_reward,evaluation/episode.return,evaluation/episode.length,evaluation/episode.duration,evaluation/episode.normalized_return,step |
| 825.35,2.8454338985244405,169.84973273932687,80.2,0.10753800868988037,5.841690394994217,1 |
| 8156.5,4.005446208736875,2003.267252104075,629.6,0.5151860475540161,62.17528349255938,100000 |
| 19909.55,4.0669473595383945,1678.765361559305,528.65,0.444842004776001,52.20463727135738,200000 |
| 30035.7,4.190071635130852,1666.9771028090763,520.4,0.4275181770324707,51.84243119186367,300000 |
| 40931.4,4.114638831869425,1706.5812482829879,535.6,0.43217830657958983,53.059308303890575,400000 |
| 51595.2,4.026773241281342,1784.3907882324645,561.45,0.45618656873703,55.45008449988838,500000 |
| 63667.6,3.9524222011412133,2001.9583359751657,625.95,0.5127526998519898,62.13506573101519,600000 |
| 75774.05,4.093328565077235,1821.6517680539844,578.75,0.4554393529891968,56.5949654959036,700000 |
| 86424.3,3.9951821418335056,1570.013020411386,492.9,0.4051892638206482,48.863112457763805,800000 |
| 96653.65,4.05461131406702,1725.871344794258,539.85,0.4538187861442566,53.65201587660711,900000 |
| 107658.2,3.9642261841463577,1743.4793794374618,549.05,0.4453374743461609,54.19304041049602,1000000 |
|
|
