CoolFace
Modelpublic

CodeDraco/arbiter-grpo-v2

sourceHugging Faceupdated 5mo agoView on Hugging Face
0likes4downloads
training_summary.json210 linesDownload Raw Back to root
1{2  "episodes": 100,3  "level": 3,4  "terminal_only": false,5  "final_mean_reward": 5.9,6  "reward_curve": [7    5.85,8    4.875,9    5.925000000000001,10    4.3500000000000005,11    6.375,12    6.825,13    4.725,14    6.15,15    7.125,16    5.175,17    5.775,18    5.324999999999999,19    5.85,20    4.65,21    6.375,22    4.575,23    4.949999999999999,24    6.0,25    5.7,26    6.0,27    5.7,28    4.7250000000000005,29    7.199999999999999,30    5.475,31    4.95,32    6.3,33    5.4,34    7.199999999999999,35    5.4750000000000005,36    5.550000000000001,37    4.575,38    5.55,39    7.35,40    5.4,41    5.0249999999999995,42    6.5249999999999995,43    7.3500000000000005,44    5.625,45    4.575,46    5.85,47    7.275,48    5.775,49    6.375,50    5.625,51    5.625,52    5.475,53    6.45,54    5.325,55    6.375,56    5.174999999999999,57    5.7,58    7.35,59    6.15,60    6.9,61    5.475,62    6.300000000000001,63    4.575,64    6.3,65    5.625,66    7.425000000000001,67    4.425,68    6.9750000000000005,69    5.175,70    5.699999999999999,71    6.225,72    4.8,73    5.325,74    5.325,75    6.225,76    6.15,77    4.875,78    5.775,79    5.175,80    4.875,81    5.475,82    6.525,83    6.375,84    5.625,85    5.1,86    4.5,87    4.65,88    6.15,89    5.85,90    5.324999999999999,91    5.775,92    4.65,93    6.1499999999999995,94    5.925000000000001,95    5.55,96    6.75,97    5.8500000000000005,98    5.625,99    5.625,100    6.825,101    5.475,102    6.9,103    5.025,104    6.15,105    6.225,106    5.325107  ],108  "defender_evasion": [109    1.0,110    1.0,111    1.0,112    1.0,113    1.0,114    1.0,115    1.0,116    1.0,117    1.0,118    1.0,119    1.0,120    1.0,121    1.0,122    1.0,123    1.0,124    1.0,125    1.0,126    1.0,127    1.0,128    1.0,129    1.0,130    1.0,131    1.0,132    1.0,133    1.0,134    1.0,135    1.0,136    1.0,137    1.0,138    1.0,139    1.0,140    1.0,141    1.0,142    1.0,143    1.0,144    1.0,145    1.0,146    1.0,147    1.0,148    1.0,149    1.0,150    1.0,151    1.0,152    1.0,153    1.0,154    1.0,155    1.0,156    1.0,157    1.0,158    1.0,159    1.0,160    1.0,161    1.0,162    1.0,163    1.0,164    1.0,165    1.0,166    1.0,167    1.0,168    1.0,169    1.0,170    1.0,171    1.0,172    1.0,173    1.0,174    1.0,175    1.0,176    1.0,177    1.0,178    1.0,179    1.0,180    1.0,181    1.0,182    1.0,183    1.0,184    1.0,185    1.0,186    1.0,187    1.0,188    1.0,189    1.0,190    1.0,191    1.0,192    1.0,193    1.0,194    1.0,195    1.0,196    1.0,197    1.0,198    1.0,199    1.0,200    1.0,201    1.0,202    1.0,203    1.0,204    1.0,205    1.0,206    1.0,207    1.0,208    1.0209  ]210}