Solshine commited on
Commit
d6a8a17
·
verified ·
1 Parent(s): 7f38c37

add checkpoints/grpo_probe_arm_priordev/trainloss.csv (T2-arms-controls)

Browse files
checkpoints/grpo_probe_arm_priordev/trainloss.csv ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,mean_reward,frac_std_pos,rvp,rho_bar,pg_loss,wall_s
2
+ 1,0.049931153655052185,1.0,0.0075,0.25,-0.17561253905296326,28.4
3
+ 2,0.07473951578140259,1.0,0.0168,0.25,0.01736651360988617,25.0
4
+ 3,0.13705000281333923,1.0,0.0097,0.4167,-0.09414920210838318,28.3
5
+ 4,0.047702398151159286,1.0,0.0089,0.375,0.1451098471879959,27.5
6
+ 5,-0.044999998062849045,1.0,0.0003,0.3,-0.08624193072319031,30.8
7
+ 6,0.0,0.0,0.0,0.25,0.0,25.7
8
+ 7,-0.04500000178813934,1.0,0.0005,0.2143,0.20585304126143456,30.8
9
+ 8,-0.019999999552965164,1.0,0.0006,0.1875,0.12801162898540497,28.1
10
+ 9,-0.03999999910593033,1.0,0.0006,0.1667,0.13474534451961517,29.6
11
+ 10,-0.02500000037252903,1.0,0.0019,0.15,-0.07433541119098663,28.8
12
+ 11,0.06830542534589767,1.0,0.014,0.1591,-0.1384328454732895,27.0
13
+ 12,-0.004999999888241291,1.0,0.0001,0.1458,0.12472113966941833,29.4
14
+ 13,-0.06000000238418579,1.0,0.0018,0.1346,-0.14532572031021118,29.9
15
+ 14,-0.014999999664723873,1.0,0.0007,0.125,-0.022343039512634277,28.3
16
+ 15,0.04789253696799278,1.0,0.0069,0.1333,-0.0748353973031044,30.6
17
+ 16,0.04653722047805786,0.0,0.0,0.1875,0.0,25.8
18
+ 17,-0.004999999888241291,1.0,0.0001,0.1765,-0.11690118908882141,28.1
19
+ 18,-0.004999999888241291,1.0,0.0001,0.1667,-0.21332520246505737,28.6
20
+ 19,-0.014999999664723873,1.0,0.0007,0.1579,-0.2583386301994324,30.7
21
+ 20,-0.03999999910593033,1.0,0.0014,0.15,-0.07156738638877869,28.8
22
+ 21,-0.019999999552965164,1.0,0.0006,0.1429,-0.40103577077388763,27.4