Auto-sync: 2026-06-27 18:45:15
Browse files
results/h16_policy_ckpt_nonexpert_policy_bc5_bestpt_field_sweep_summary.json
ADDED
|
@@ -0,0 +1,985 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run_root": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep",
|
| 3 |
+
"baseline_h4_policy_success": 0.2967,
|
| 4 |
+
"baseline_h16_policy_success": 0.29739130434782607,
|
| 5 |
+
"num_result_files": 12,
|
| 6 |
+
"configs": [
|
| 7 |
+
{
|
| 8 |
+
"config": "k64_sigma0.50",
|
| 9 |
+
"completed_seeds": [
|
| 10 |
+
0,
|
| 11 |
+
1,
|
| 12 |
+
2
|
| 13 |
+
],
|
| 14 |
+
"num_completed": 3,
|
| 15 |
+
"mean_success": 0.26492753623188403,
|
| 16 |
+
"std_success": 0.021252524962114057,
|
| 17 |
+
"mean_progress": 0.5022954986964527,
|
| 18 |
+
"mean_action_mse_to_best": 0.48412693971201126,
|
| 19 |
+
"absolute_gain_vs_h4_baseline": -0.03177246376811599,
|
| 20 |
+
"absolute_gain_vs_h16_policy": -0.03246376811594204
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"config": "k8_sigma0.10",
|
| 24 |
+
"completed_seeds": [
|
| 25 |
+
0,
|
| 26 |
+
1,
|
| 27 |
+
2
|
| 28 |
+
],
|
| 29 |
+
"num_completed": 3,
|
| 30 |
+
"mean_success": 0.26318840579710145,
|
| 31 |
+
"std_success": 0.018267769572856495,
|
| 32 |
+
"mean_progress": 0.5032286144989886,
|
| 33 |
+
"mean_action_mse_to_best": 0.46685748584406533,
|
| 34 |
+
"absolute_gain_vs_h4_baseline": -0.033511594202898565,
|
| 35 |
+
"absolute_gain_vs_h16_policy": -0.034202898550724614
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"config": "k32_sigma0.35",
|
| 39 |
+
"completed_seeds": [
|
| 40 |
+
0,
|
| 41 |
+
1,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"num_completed": 3,
|
| 45 |
+
"mean_success": 0.26028985507246377,
|
| 46 |
+
"std_success": 0.02315940215123268,
|
| 47 |
+
"mean_progress": 0.501555436926462,
|
| 48 |
+
"mean_action_mse_to_best": 0.47715315959483817,
|
| 49 |
+
"absolute_gain_vs_h4_baseline": -0.03641014492753625,
|
| 50 |
+
"absolute_gain_vs_h16_policy": -0.0371014492753623
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"config": "k16_sigma0.20",
|
| 54 |
+
"completed_seeds": [
|
| 55 |
+
0,
|
| 56 |
+
1,
|
| 57 |
+
2
|
| 58 |
+
],
|
| 59 |
+
"num_completed": 3,
|
| 60 |
+
"mean_success": 0.25623188405797104,
|
| 61 |
+
"std_success": 0.02125252496211404,
|
| 62 |
+
"mean_progress": 0.49594171314534014,
|
| 63 |
+
"mean_action_mse_to_best": 0.47141848932249825,
|
| 64 |
+
"absolute_gain_vs_h4_baseline": -0.04046811594202898,
|
| 65 |
+
"absolute_gain_vs_h16_policy": -0.04115942028985503
|
| 66 |
+
}
|
| 67 |
+
],
|
| 68 |
+
"best": {
|
| 69 |
+
"config": "k64_sigma0.50",
|
| 70 |
+
"completed_seeds": [
|
| 71 |
+
0,
|
| 72 |
+
1,
|
| 73 |
+
2
|
| 74 |
+
],
|
| 75 |
+
"num_completed": 3,
|
| 76 |
+
"mean_success": 0.26492753623188403,
|
| 77 |
+
"std_success": 0.021252524962114057,
|
| 78 |
+
"mean_progress": 0.5022954986964527,
|
| 79 |
+
"mean_action_mse_to_best": 0.48412693971201126,
|
| 80 |
+
"absolute_gain_vs_h4_baseline": -0.03177246376811599,
|
| 81 |
+
"absolute_gain_vs_h16_policy": -0.03246376811594204
|
| 82 |
+
},
|
| 83 |
+
"rows": [
|
| 84 |
+
{
|
| 85 |
+
"config": "k16_sigma0.20",
|
| 86 |
+
"seed": 0,
|
| 87 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k16_sigma0.20/seed_0/online_rollout.json",
|
| 88 |
+
"selection_mode": "field",
|
| 89 |
+
"num_candidates": 16,
|
| 90 |
+
"candidate_sigma": 0.2,
|
| 91 |
+
"field_optim_steps": 0,
|
| 92 |
+
"field_optim_step_size": 0.0,
|
| 93 |
+
"field_optim_trust_radius": 0.0,
|
| 94 |
+
"field_optim_l2_penalty": 0.0,
|
| 95 |
+
"retrieval_neighbors": 0,
|
| 96 |
+
"num_groups": 575,
|
| 97 |
+
"policy_rollout_success_rate": 0.23304347826086957,
|
| 98 |
+
"policy_rollout_progress": 0.481306260572139,
|
| 99 |
+
"oracle_success_rate": 0.8573913043478261,
|
| 100 |
+
"action_mse_to_best": 0.45690098340744556,
|
| 101 |
+
"per_task": {
|
| 102 |
+
"LiftPegUpright-v1": {
|
| 103 |
+
"action_mse_to_best": 0.36156272988036736,
|
| 104 |
+
"expert_success_rate": 0.8865979381443299,
|
| 105 |
+
"num_groups": 97,
|
| 106 |
+
"oracle_success_rate": 0.9278350515463918,
|
| 107 |
+
"policy_expert_regret": 1.1752674995931154,
|
| 108 |
+
"policy_oracle_regret": 1.22814422523238,
|
| 109 |
+
"policy_rollout_progress": 0.5436697447115613,
|
| 110 |
+
"policy_rollout_success_rate": 0.14432989690721648,
|
| 111 |
+
"restore_max_error": 4.76837158203125e-07
|
| 112 |
+
},
|
| 113 |
+
"PickCube-v1": {
|
| 114 |
+
"action_mse_to_best": 0.35019572166940915,
|
| 115 |
+
"expert_success_rate": 0.9375,
|
| 116 |
+
"num_groups": 208,
|
| 117 |
+
"oracle_success_rate": 0.9471153846153846,
|
| 118 |
+
"policy_expert_regret": 1.2117853179879603,
|
| 119 |
+
"policy_oracle_regret": 1.2184518920419998,
|
| 120 |
+
"policy_rollout_progress": 0.5193353609664393,
|
| 121 |
+
"policy_rollout_success_rate": 0.1875,
|
| 122 |
+
"restore_max_error": 4.76837158203125e-07
|
| 123 |
+
},
|
| 124 |
+
"PullCube-v1": {
|
| 125 |
+
"action_mse_to_best": 0.7272258265935755,
|
| 126 |
+
"expert_success_rate": 0.19480519480519481,
|
| 127 |
+
"num_groups": 77,
|
| 128 |
+
"oracle_success_rate": 0.36363636363636365,
|
| 129 |
+
"policy_expert_regret": 0.25227385023971655,
|
| 130 |
+
"policy_oracle_regret": 0.5023551824224459,
|
| 131 |
+
"policy_rollout_progress": 0.28333891163785735,
|
| 132 |
+
"policy_rollout_success_rate": 0.12987012987012986,
|
| 133 |
+
"restore_max_error": 4.76837158203125e-07
|
| 134 |
+
},
|
| 135 |
+
"PushCube-v1": {
|
| 136 |
+
"action_mse_to_best": 0.45739054711575206,
|
| 137 |
+
"expert_success_rate": 0.8617021276595744,
|
| 138 |
+
"num_groups": 94,
|
| 139 |
+
"oracle_success_rate": 0.9893617021276596,
|
| 140 |
+
"policy_expert_regret": 0.595260574304043,
|
| 141 |
+
"policy_oracle_regret": 0.6943609684388689,
|
| 142 |
+
"policy_rollout_progress": 0.6673411592207057,
|
| 143 |
+
"policy_rollout_success_rate": 0.6382978723404256,
|
| 144 |
+
"restore_max_error": 4.76837158203125e-07
|
| 145 |
+
},
|
| 146 |
+
"StackCube-v1": {
|
| 147 |
+
"action_mse_to_best": 0.5637845502733582,
|
| 148 |
+
"expert_success_rate": 0.6767676767676768,
|
| 149 |
+
"num_groups": 99,
|
| 150 |
+
"oracle_success_rate": 0.8585858585858586,
|
| 151 |
+
"policy_expert_regret": 1.194501390812373,
|
| 152 |
+
"policy_oracle_regret": 1.3921601070900156,
|
| 153 |
+
"policy_rollout_progress": 0.3176385287684624,
|
| 154 |
+
"policy_rollout_success_rate": 0.1111111111111111,
|
| 155 |
+
"restore_max_error": 3.948807716369629e-07
|
| 156 |
+
}
|
| 157 |
+
}
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"config": "k16_sigma0.20",
|
| 161 |
+
"seed": 1,
|
| 162 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k16_sigma0.20/seed_1/online_rollout.json",
|
| 163 |
+
"selection_mode": "field",
|
| 164 |
+
"num_candidates": 16,
|
| 165 |
+
"candidate_sigma": 0.2,
|
| 166 |
+
"field_optim_steps": 0,
|
| 167 |
+
"field_optim_step_size": 0.0,
|
| 168 |
+
"field_optim_trust_radius": 0.0,
|
| 169 |
+
"field_optim_l2_penalty": 0.0,
|
| 170 |
+
"retrieval_neighbors": 0,
|
| 171 |
+
"num_groups": 575,
|
| 172 |
+
"policy_rollout_success_rate": 0.2608695652173913,
|
| 173 |
+
"policy_rollout_progress": 0.4960327315978382,
|
| 174 |
+
"oracle_success_rate": 0.8695652173913043,
|
| 175 |
+
"action_mse_to_best": 0.4718579385429621,
|
| 176 |
+
"per_task": {
|
| 177 |
+
"LiftPegUpright-v1": {
|
| 178 |
+
"action_mse_to_best": 0.38650470532773606,
|
| 179 |
+
"expert_success_rate": 0.8584070796460177,
|
| 180 |
+
"num_groups": 113,
|
| 181 |
+
"oracle_success_rate": 0.9380530973451328,
|
| 182 |
+
"policy_expert_regret": 1.2091129610760023,
|
| 183 |
+
"policy_oracle_regret": 1.2993210304891114,
|
| 184 |
+
"policy_rollout_progress": 0.5178761330589784,
|
| 185 |
+
"policy_rollout_success_rate": 0.11504424778761062,
|
| 186 |
+
"restore_max_error": 4.76837158203125e-07
|
| 187 |
+
},
|
| 188 |
+
"PickCube-v1": {
|
| 189 |
+
"action_mse_to_best": 0.37929783941691986,
|
| 190 |
+
"expert_success_rate": 0.9402173913043478,
|
| 191 |
+
"num_groups": 184,
|
| 192 |
+
"oracle_success_rate": 0.9456521739130435,
|
| 193 |
+
"policy_expert_regret": 1.212091081077233,
|
| 194 |
+
"policy_oracle_regret": 1.2196279860445824,
|
| 195 |
+
"policy_rollout_progress": 0.5235967556034903,
|
| 196 |
+
"policy_rollout_success_rate": 0.1956521739130435,
|
| 197 |
+
"restore_max_error": 4.76837158203125e-07
|
| 198 |
+
},
|
| 199 |
+
"PullCube-v1": {
|
| 200 |
+
"action_mse_to_best": 0.6850374752631117,
|
| 201 |
+
"expert_success_rate": 0.25,
|
| 202 |
+
"num_groups": 76,
|
| 203 |
+
"oracle_success_rate": 0.40789473684210525,
|
| 204 |
+
"policy_expert_regret": 0.388238598372003,
|
| 205 |
+
"policy_oracle_regret": 0.5268601372494901,
|
| 206 |
+
"policy_rollout_progress": 0.29480838469278653,
|
| 207 |
+
"policy_rollout_success_rate": 0.15789473684210525,
|
| 208 |
+
"restore_max_error": 4.76837158203125e-07
|
| 209 |
+
},
|
| 210 |
+
"PushCube-v1": {
|
| 211 |
+
"action_mse_to_best": 0.4314351695346403,
|
| 212 |
+
"expert_success_rate": 0.8198198198198198,
|
| 213 |
+
"num_groups": 111,
|
| 214 |
+
"oracle_success_rate": 1.0,
|
| 215 |
+
"policy_expert_regret": 0.4830353117740906,
|
| 216 |
+
"policy_oracle_regret": 0.5852147505895512,
|
| 217 |
+
"policy_rollout_progress": 0.7210915557167552,
|
| 218 |
+
"policy_rollout_success_rate": 0.6936936936936937,
|
| 219 |
+
"restore_max_error": 4.76837158203125e-07
|
| 220 |
+
},
|
| 221 |
+
"StackCube-v1": {
|
| 222 |
+
"action_mse_to_best": 0.636267346913343,
|
| 223 |
+
"expert_success_rate": 0.6923076923076923,
|
| 224 |
+
"num_groups": 91,
|
| 225 |
+
"oracle_success_rate": 0.8571428571428571,
|
| 226 |
+
"policy_expert_regret": 1.2156181492648281,
|
| 227 |
+
"policy_oracle_regret": 1.393361678490272,
|
| 228 |
+
"policy_rollout_progress": 0.30670785363558883,
|
| 229 |
+
"policy_rollout_success_rate": 0.13186813186813187,
|
| 230 |
+
"restore_max_error": 3.948807716369629e-07
|
| 231 |
+
}
|
| 232 |
+
}
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"config": "k16_sigma0.20",
|
| 236 |
+
"seed": 2,
|
| 237 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k16_sigma0.20/seed_2/online_rollout.json",
|
| 238 |
+
"selection_mode": "field",
|
| 239 |
+
"num_candidates": 16,
|
| 240 |
+
"candidate_sigma": 0.2,
|
| 241 |
+
"field_optim_steps": 0,
|
| 242 |
+
"field_optim_step_size": 0.0,
|
| 243 |
+
"field_optim_trust_radius": 0.0,
|
| 244 |
+
"field_optim_l2_penalty": 0.0,
|
| 245 |
+
"retrieval_neighbors": 0,
|
| 246 |
+
"num_groups": 575,
|
| 247 |
+
"policy_rollout_success_rate": 0.2747826086956522,
|
| 248 |
+
"policy_rollout_progress": 0.5104861472660432,
|
| 249 |
+
"oracle_success_rate": 0.8765217391304347,
|
| 250 |
+
"action_mse_to_best": 0.485496546017087,
|
| 251 |
+
"per_task": {
|
| 252 |
+
"LiftPegUpright-v1": {
|
| 253 |
+
"action_mse_to_best": 0.3917640429184151,
|
| 254 |
+
"expert_success_rate": 0.8229166666666666,
|
| 255 |
+
"num_groups": 96,
|
| 256 |
+
"oracle_success_rate": 0.9270833333333334,
|
| 257 |
+
"policy_expert_regret": 1.0213091777016718,
|
| 258 |
+
"policy_oracle_regret": 1.1147574900339048,
|
| 259 |
+
"policy_rollout_progress": 0.6075957007706165,
|
| 260 |
+
"policy_rollout_success_rate": 0.19791666666666666,
|
| 261 |
+
"restore_max_error": 3.5762786865234375e-07
|
| 262 |
+
},
|
| 263 |
+
"PickCube-v1": {
|
| 264 |
+
"action_mse_to_best": 0.3677950848947571,
|
| 265 |
+
"expert_success_rate": 0.9444444444444444,
|
| 266 |
+
"num_groups": 198,
|
| 267 |
+
"oracle_success_rate": 0.9595959595959596,
|
| 268 |
+
"policy_expert_regret": 1.1760698302526666,
|
| 269 |
+
"policy_oracle_regret": 1.183153280781375,
|
| 270 |
+
"policy_rollout_progress": 0.5374011066977424,
|
| 271 |
+
"policy_rollout_success_rate": 0.22727272727272727,
|
| 272 |
+
"restore_max_error": 4.76837158203125e-07
|
| 273 |
+
},
|
| 274 |
+
"PullCube-v1": {
|
| 275 |
+
"action_mse_to_best": 0.753667805240386,
|
| 276 |
+
"expert_success_rate": 0.24444444444444444,
|
| 277 |
+
"num_groups": 90,
|
| 278 |
+
"oracle_success_rate": 0.4666666666666667,
|
| 279 |
+
"policy_expert_regret": 0.3977184874833458,
|
| 280 |
+
"policy_oracle_regret": 0.6888696794398129,
|
| 281 |
+
"policy_rollout_progress": 0.26258616872752705,
|
| 282 |
+
"policy_rollout_success_rate": 0.12222222222222222,
|
| 283 |
+
"restore_max_error": 4.0978193283081055e-07
|
| 284 |
+
},
|
| 285 |
+
"PushCube-v1": {
|
| 286 |
+
"action_mse_to_best": 0.43290947510464356,
|
| 287 |
+
"expert_success_rate": 0.8514851485148515,
|
| 288 |
+
"num_groups": 101,
|
| 289 |
+
"oracle_success_rate": 1.0,
|
| 290 |
+
"policy_expert_regret": 0.41660966023360146,
|
| 291 |
+
"policy_oracle_regret": 0.4726692643200997,
|
| 292 |
+
"policy_rollout_progress": 0.7748554881551478,
|
| 293 |
+
"policy_rollout_success_rate": 0.7524752475247525,
|
| 294 |
+
"restore_max_error": 4.76837158203125e-07
|
| 295 |
+
},
|
| 296 |
+
"StackCube-v1": {
|
| 297 |
+
"action_mse_to_best": 0.6352642174810171,
|
| 298 |
+
"expert_success_rate": 0.7666666666666667,
|
| 299 |
+
"num_groups": 90,
|
| 300 |
+
"oracle_success_rate": 0.9111111111111111,
|
| 301 |
+
"policy_expert_regret": 1.3953763832648596,
|
| 302 |
+
"policy_oracle_regret": 1.505328611863984,
|
| 303 |
+
"policy_rollout_progress": 0.2989085420966148,
|
| 304 |
+
"policy_rollout_success_rate": 0.07777777777777778,
|
| 305 |
+
"restore_max_error": 4.76837158203125e-07
|
| 306 |
+
}
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"config": "k32_sigma0.35",
|
| 311 |
+
"seed": 0,
|
| 312 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k32_sigma0.35/seed_0/online_rollout.json",
|
| 313 |
+
"selection_mode": "field",
|
| 314 |
+
"num_candidates": 32,
|
| 315 |
+
"candidate_sigma": 0.35,
|
| 316 |
+
"field_optim_steps": 0,
|
| 317 |
+
"field_optim_step_size": 0.0,
|
| 318 |
+
"field_optim_trust_radius": 0.0,
|
| 319 |
+
"field_optim_l2_penalty": 0.0,
|
| 320 |
+
"retrieval_neighbors": 0,
|
| 321 |
+
"num_groups": 575,
|
| 322 |
+
"policy_rollout_success_rate": 0.23478260869565218,
|
| 323 |
+
"policy_rollout_progress": 0.48394788081616,
|
| 324 |
+
"oracle_success_rate": 0.8573913043478261,
|
| 325 |
+
"action_mse_to_best": 0.45940005344541174,
|
| 326 |
+
"per_task": {
|
| 327 |
+
"LiftPegUpright-v1": {
|
| 328 |
+
"action_mse_to_best": 0.3602740007654293,
|
| 329 |
+
"expert_success_rate": 0.8865979381443299,
|
| 330 |
+
"num_groups": 97,
|
| 331 |
+
"oracle_success_rate": 0.9278350515463918,
|
| 332 |
+
"policy_expert_regret": 1.1945109934229212,
|
| 333 |
+
"policy_oracle_regret": 1.2472596925865744,
|
| 334 |
+
"policy_rollout_progress": 0.5349013708608666,
|
| 335 |
+
"policy_rollout_success_rate": 0.13402061855670103,
|
| 336 |
+
"restore_max_error": 4.76837158203125e-07
|
| 337 |
+
},
|
| 338 |
+
"PickCube-v1": {
|
| 339 |
+
"action_mse_to_best": 0.3544642553628924,
|
| 340 |
+
"expert_success_rate": 0.9375,
|
| 341 |
+
"num_groups": 208,
|
| 342 |
+
"oracle_success_rate": 0.9471153846153846,
|
| 343 |
+
"policy_expert_regret": 1.2080141726524185,
|
| 344 |
+
"policy_oracle_regret": 1.2146807467064578,
|
| 345 |
+
"policy_rollout_progress": 0.5231065063019812,
|
| 346 |
+
"policy_rollout_success_rate": 0.1875,
|
| 347 |
+
"restore_max_error": 4.76837158203125e-07
|
| 348 |
+
},
|
| 349 |
+
"PullCube-v1": {
|
| 350 |
+
"action_mse_to_best": 0.7321509141716864,
|
| 351 |
+
"expert_success_rate": 0.19480519480519481,
|
| 352 |
+
"num_groups": 77,
|
| 353 |
+
"oracle_success_rate": 0.36363636363636365,
|
| 354 |
+
"policy_expert_regret": 0.2739613295665809,
|
| 355 |
+
"policy_oracle_regret": 0.4556723123343734,
|
| 356 |
+
"policy_rollout_progress": 0.2960374831863038,
|
| 357 |
+
"policy_rollout_success_rate": 0.14285714285714285,
|
| 358 |
+
"restore_max_error": 4.76837158203125e-07
|
| 359 |
+
},
|
| 360 |
+
"PushCube-v1": {
|
| 361 |
+
"action_mse_to_best": 0.45896308385628337,
|
| 362 |
+
"expert_success_rate": 0.8617021276595744,
|
| 363 |
+
"num_groups": 94,
|
| 364 |
+
"oracle_success_rate": 0.9893617021276596,
|
| 365 |
+
"policy_expert_regret": 0.5975629717428633,
|
| 366 |
+
"policy_oracle_regret": 0.6773244559447816,
|
| 367 |
+
"policy_rollout_progress": 0.6737393738424524,
|
| 368 |
+
"policy_rollout_success_rate": 0.648936170212766,
|
| 369 |
+
"restore_max_error": 4.76837158203125e-07
|
| 370 |
+
},
|
| 371 |
+
"StackCube-v1": {
|
| 372 |
+
"action_mse_to_best": 0.5652700734108386,
|
| 373 |
+
"expert_success_rate": 0.6767676767676768,
|
| 374 |
+
"num_groups": 99,
|
| 375 |
+
"oracle_success_rate": 0.8585858585858586,
|
| 376 |
+
"policy_expert_regret": 1.1944423656571994,
|
| 377 |
+
"policy_oracle_regret": 1.3921010819348423,
|
| 378 |
+
"policy_rollout_progress": 0.31769755392363574,
|
| 379 |
+
"policy_rollout_success_rate": 0.1111111111111111,
|
| 380 |
+
"restore_max_error": 3.948807716369629e-07
|
| 381 |
+
}
|
| 382 |
+
}
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"config": "k32_sigma0.35",
|
| 386 |
+
"seed": 1,
|
| 387 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k32_sigma0.35/seed_1/online_rollout.json",
|
| 388 |
+
"selection_mode": "field",
|
| 389 |
+
"num_candidates": 32,
|
| 390 |
+
"candidate_sigma": 0.35,
|
| 391 |
+
"field_optim_steps": 0,
|
| 392 |
+
"field_optim_step_size": 0.0,
|
| 393 |
+
"field_optim_trust_radius": 0.0,
|
| 394 |
+
"field_optim_l2_penalty": 0.0,
|
| 395 |
+
"retrieval_neighbors": 0,
|
| 396 |
+
"num_groups": 575,
|
| 397 |
+
"policy_rollout_success_rate": 0.26608695652173914,
|
| 398 |
+
"policy_rollout_progress": 0.501970462889775,
|
| 399 |
+
"oracle_success_rate": 0.8695652173913043,
|
| 400 |
+
"action_mse_to_best": 0.4788765658988901,
|
| 401 |
+
"per_task": {
|
| 402 |
+
"LiftPegUpright-v1": {
|
| 403 |
+
"action_mse_to_best": 0.38885907191717256,
|
| 404 |
+
"expert_success_rate": 0.8584070796460177,
|
| 405 |
+
"num_groups": 113,
|
| 406 |
+
"oracle_success_rate": 0.9380530973451328,
|
| 407 |
+
"policy_expert_regret": 1.2098119463277075,
|
| 408 |
+
"policy_oracle_regret": 1.3000200157408166,
|
| 409 |
+
"policy_rollout_progress": 0.5171771478072732,
|
| 410 |
+
"policy_rollout_success_rate": 0.11504424778761062,
|
| 411 |
+
"restore_max_error": 4.76837158203125e-07
|
| 412 |
+
},
|
| 413 |
+
"PickCube-v1": {
|
| 414 |
+
"action_mse_to_best": 0.38886870478239394,
|
| 415 |
+
"expert_success_rate": 0.9402173913043478,
|
| 416 |
+
"num_groups": 184,
|
| 417 |
+
"oracle_success_rate": 0.9456521739130435,
|
| 418 |
+
"policy_expert_regret": 1.210059181999658,
|
| 419 |
+
"policy_oracle_regret": 1.2175960869670077,
|
| 420 |
+
"policy_rollout_progress": 0.5256286546810651,
|
| 421 |
+
"policy_rollout_success_rate": 0.1956521739130435,
|
| 422 |
+
"restore_max_error": 4.76837158203125e-07
|
| 423 |
+
},
|
| 424 |
+
"PullCube-v1": {
|
| 425 |
+
"action_mse_to_best": 0.7087747321194527,
|
| 426 |
+
"expert_success_rate": 0.25,
|
| 427 |
+
"num_groups": 76,
|
| 428 |
+
"oracle_success_rate": 0.40789473684210525,
|
| 429 |
+
"policy_expert_regret": 0.34390143371236165,
|
| 430 |
+
"policy_oracle_regret": 0.5295321655851838,
|
| 431 |
+
"policy_rollout_progress": 0.2927222623685865,
|
| 432 |
+
"policy_rollout_success_rate": 0.15789473684210525,
|
| 433 |
+
"restore_max_error": 4.76837158203125e-07
|
| 434 |
+
},
|
| 435 |
+
"PushCube-v1": {
|
| 436 |
+
"action_mse_to_best": 0.43596628912397334,
|
| 437 |
+
"expert_success_rate": 0.8198198198198198,
|
| 438 |
+
"num_groups": 111,
|
| 439 |
+
"oracle_success_rate": 1.0,
|
| 440 |
+
"policy_expert_regret": 0.4955169083298864,
|
| 441 |
+
"policy_oracle_regret": 0.5461092336220784,
|
| 442 |
+
"policy_rollout_progress": 0.7421790546662098,
|
| 443 |
+
"policy_rollout_success_rate": 0.7117117117117117,
|
| 444 |
+
"restore_max_error": 4.76837158203125e-07
|
| 445 |
+
},
|
| 446 |
+
"StackCube-v1": {
|
| 447 |
+
"action_mse_to_best": 0.63298869067496,
|
| 448 |
+
"expert_success_rate": 0.6923076923076923,
|
| 449 |
+
"num_groups": 91,
|
| 450 |
+
"oracle_success_rate": 0.8571428571428571,
|
| 451 |
+
"policy_expert_regret": 1.1943308491628248,
|
| 452 |
+
"policy_oracle_regret": 1.3720743783882685,
|
| 453 |
+
"policy_rollout_progress": 0.3170061427485812,
|
| 454 |
+
"policy_rollout_success_rate": 0.14285714285714285,
|
| 455 |
+
"restore_max_error": 3.948807716369629e-07
|
| 456 |
+
}
|
| 457 |
+
}
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"config": "k32_sigma0.35",
|
| 461 |
+
"seed": 2,
|
| 462 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k32_sigma0.35/seed_2/online_rollout.json",
|
| 463 |
+
"selection_mode": "field",
|
| 464 |
+
"num_candidates": 32,
|
| 465 |
+
"candidate_sigma": 0.35,
|
| 466 |
+
"field_optim_steps": 0,
|
| 467 |
+
"field_optim_step_size": 0.0,
|
| 468 |
+
"field_optim_trust_radius": 0.0,
|
| 469 |
+
"field_optim_l2_penalty": 0.0,
|
| 470 |
+
"retrieval_neighbors": 0,
|
| 471 |
+
"num_groups": 575,
|
| 472 |
+
"policy_rollout_success_rate": 0.28,
|
| 473 |
+
"policy_rollout_progress": 0.5187479670734509,
|
| 474 |
+
"oracle_success_rate": 0.8765217391304347,
|
| 475 |
+
"action_mse_to_best": 0.4931828594402127,
|
| 476 |
+
"per_task": {
|
| 477 |
+
"LiftPegUpright-v1": {
|
| 478 |
+
"action_mse_to_best": 0.39279332409690443,
|
| 479 |
+
"expert_success_rate": 0.8229166666666666,
|
| 480 |
+
"num_groups": 96,
|
| 481 |
+
"oracle_success_rate": 0.9270833333333334,
|
| 482 |
+
"policy_expert_regret": 0.9923351087297002,
|
| 483 |
+
"policy_oracle_regret": 1.0861823692296941,
|
| 484 |
+
"policy_rollout_progress": 0.6229077071572343,
|
| 485 |
+
"policy_rollout_success_rate": 0.19791666666666666,
|
| 486 |
+
"restore_max_error": 3.5762786865234375e-07
|
| 487 |
+
},
|
| 488 |
+
"PickCube-v1": {
|
| 489 |
+
"action_mse_to_best": 0.36930092557737926,
|
| 490 |
+
"expert_success_rate": 0.9444444444444444,
|
| 491 |
+
"num_groups": 198,
|
| 492 |
+
"oracle_success_rate": 0.9595959595959596,
|
| 493 |
+
"policy_expert_regret": 1.170777508471575,
|
| 494 |
+
"policy_oracle_regret": 1.1778609590002833,
|
| 495 |
+
"policy_rollout_progress": 0.542693428478834,
|
| 496 |
+
"policy_rollout_success_rate": 0.22727272727272727,
|
| 497 |
+
"restore_max_error": 4.76837158203125e-07
|
| 498 |
+
},
|
| 499 |
+
"PullCube-v1": {
|
| 500 |
+
"action_mse_to_best": 0.7964321372616622,
|
| 501 |
+
"expert_success_rate": 0.24444444444444444,
|
| 502 |
+
"num_groups": 90,
|
| 503 |
+
"oracle_success_rate": 0.4666666666666667,
|
| 504 |
+
"policy_expert_regret": 0.33501800801604986,
|
| 505 |
+
"policy_oracle_regret": 0.6114743017281096,
|
| 506 |
+
"policy_rollout_progress": 0.28941386095765564,
|
| 507 |
+
"policy_rollout_success_rate": 0.15555555555555556,
|
| 508 |
+
"restore_max_error": 4.0978193283081055e-07
|
| 509 |
+
},
|
| 510 |
+
"PushCube-v1": {
|
| 511 |
+
"action_mse_to_best": 0.4326566268902014,
|
| 512 |
+
"expert_success_rate": 0.8514851485148515,
|
| 513 |
+
"num_groups": 101,
|
| 514 |
+
"oracle_success_rate": 1.0,
|
| 515 |
+
"policy_expert_regret": 0.43564763532416656,
|
| 516 |
+
"policy_oracle_regret": 0.4738146951883146,
|
| 517 |
+
"policy_rollout_progress": 0.7737100572869329,
|
| 518 |
+
"policy_rollout_success_rate": 0.7524752475247525,
|
| 519 |
+
"restore_max_error": 4.76837158203125e-07
|
| 520 |
+
},
|
| 521 |
+
"StackCube-v1": {
|
| 522 |
+
"action_mse_to_best": 0.6374798903448714,
|
| 523 |
+
"expert_success_rate": 0.7666666666666667,
|
| 524 |
+
"num_groups": 90,
|
| 525 |
+
"oracle_success_rate": 0.9111111111111111,
|
| 526 |
+
"policy_expert_regret": 1.396110713481903,
|
| 527 |
+
"policy_oracle_regret": 1.5060629420810276,
|
| 528 |
+
"policy_rollout_progress": 0.29817421187957127,
|
| 529 |
+
"policy_rollout_success_rate": 0.07777777777777778,
|
| 530 |
+
"restore_max_error": 4.76837158203125e-07
|
| 531 |
+
}
|
| 532 |
+
}
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"config": "k64_sigma0.50",
|
| 536 |
+
"seed": 0,
|
| 537 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k64_sigma0.50/seed_0/online_rollout.json",
|
| 538 |
+
"selection_mode": "field",
|
| 539 |
+
"num_candidates": 64,
|
| 540 |
+
"candidate_sigma": 0.5,
|
| 541 |
+
"field_optim_steps": 0,
|
| 542 |
+
"field_optim_step_size": 0.0,
|
| 543 |
+
"field_optim_trust_radius": 0.0,
|
| 544 |
+
"field_optim_l2_penalty": 0.0,
|
| 545 |
+
"retrieval_neighbors": 0,
|
| 546 |
+
"num_groups": 575,
|
| 547 |
+
"policy_rollout_success_rate": 0.2417391304347826,
|
| 548 |
+
"policy_rollout_progress": 0.48701095541271017,
|
| 549 |
+
"oracle_success_rate": 0.8573913043478261,
|
| 550 |
+
"action_mse_to_best": 0.4654962586708691,
|
| 551 |
+
"per_task": {
|
| 552 |
+
"LiftPegUpright-v1": {
|
| 553 |
+
"action_mse_to_best": 0.36090343257354707,
|
| 554 |
+
"expert_success_rate": 0.8865979381443299,
|
| 555 |
+
"num_groups": 97,
|
| 556 |
+
"oracle_success_rate": 0.9278350515463918,
|
| 557 |
+
"policy_expert_regret": 1.1947295621191103,
|
| 558 |
+
"policy_oracle_regret": 1.2474782612827635,
|
| 559 |
+
"policy_rollout_progress": 0.5346449870116932,
|
| 560 |
+
"policy_rollout_success_rate": 0.13402061855670103,
|
| 561 |
+
"restore_max_error": 4.76837158203125e-07
|
| 562 |
+
},
|
| 563 |
+
"PickCube-v1": {
|
| 564 |
+
"action_mse_to_best": 0.3632729712049835,
|
| 565 |
+
"expert_success_rate": 0.9375,
|
| 566 |
+
"num_groups": 208,
|
| 567 |
+
"oracle_success_rate": 0.9471153846153846,
|
| 568 |
+
"policy_expert_regret": 1.2134287812318338,
|
| 569 |
+
"policy_oracle_regret": 1.2200953552858733,
|
| 570 |
+
"policy_rollout_progress": 0.5176918977225656,
|
| 571 |
+
"policy_rollout_success_rate": 0.1875,
|
| 572 |
+
"restore_max_error": 4.76837158203125e-07
|
| 573 |
+
},
|
| 574 |
+
"PullCube-v1": {
|
| 575 |
+
"action_mse_to_best": 0.7499213425757049,
|
| 576 |
+
"expert_success_rate": 0.19480519480519481,
|
| 577 |
+
"num_groups": 77,
|
| 578 |
+
"oracle_success_rate": 0.36363636363636365,
|
| 579 |
+
"policy_expert_regret": 0.17728840554882955,
|
| 580 |
+
"policy_oracle_regret": 0.3627122872351826,
|
| 581 |
+
"policy_rollout_progress": 0.3336467531497602,
|
| 582 |
+
"policy_rollout_success_rate": 0.19480519480519481,
|
| 583 |
+
"restore_max_error": 4.76837158203125e-07
|
| 584 |
+
},
|
| 585 |
+
"PushCube-v1": {
|
| 586 |
+
"action_mse_to_best": 0.45963364276797214,
|
| 587 |
+
"expert_success_rate": 0.8617021276595744,
|
| 588 |
+
"num_groups": 94,
|
| 589 |
+
"oracle_success_rate": 0.9893617021276596,
|
| 590 |
+
"policy_expert_regret": 0.597614307352837,
|
| 591 |
+
"policy_oracle_regret": 0.6773757915547554,
|
| 592 |
+
"policy_rollout_progress": 0.6736880382324787,
|
| 593 |
+
"policy_rollout_success_rate": 0.648936170212766,
|
| 594 |
+
"restore_max_error": 4.76837158203125e-07
|
| 595 |
+
},
|
| 596 |
+
"StackCube-v1": {
|
| 597 |
+
"action_mse_to_best": 0.5670952723935397,
|
| 598 |
+
"expert_success_rate": 0.6767676767676768,
|
| 599 |
+
"num_groups": 99,
|
| 600 |
+
"oracle_success_rate": 0.8585858585858586,
|
| 601 |
+
"policy_expert_regret": 1.194227340697038,
|
| 602 |
+
"policy_oracle_regret": 1.3918860569746807,
|
| 603 |
+
"policy_rollout_progress": 0.31791257888379726,
|
| 604 |
+
"policy_rollout_success_rate": 0.1111111111111111,
|
| 605 |
+
"restore_max_error": 3.948807716369629e-07
|
| 606 |
+
}
|
| 607 |
+
}
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"config": "k64_sigma0.50",
|
| 611 |
+
"seed": 1,
|
| 612 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k64_sigma0.50/seed_1/online_rollout.json",
|
| 613 |
+
"selection_mode": "field",
|
| 614 |
+
"num_candidates": 64,
|
| 615 |
+
"candidate_sigma": 0.5,
|
| 616 |
+
"field_optim_steps": 0,
|
| 617 |
+
"field_optim_step_size": 0.0,
|
| 618 |
+
"field_optim_trust_radius": 0.0,
|
| 619 |
+
"field_optim_l2_penalty": 0.0,
|
| 620 |
+
"retrieval_neighbors": 0,
|
| 621 |
+
"num_groups": 575,
|
| 622 |
+
"policy_rollout_success_rate": 0.26956521739130435,
|
| 623 |
+
"policy_rollout_progress": 0.5022271202715195,
|
| 624 |
+
"oracle_success_rate": 0.8695652173913043,
|
| 625 |
+
"action_mse_to_best": 0.4864421434927246,
|
| 626 |
+
"per_task": {
|
| 627 |
+
"LiftPegUpright-v1": {
|
| 628 |
+
"action_mse_to_best": 0.3862276160595032,
|
| 629 |
+
"expert_success_rate": 0.8584070796460177,
|
| 630 |
+
"num_groups": 113,
|
| 631 |
+
"oracle_success_rate": 0.9380530973451328,
|
| 632 |
+
"policy_expert_regret": 1.2107075293243459,
|
| 633 |
+
"policy_oracle_regret": 1.289627820385241,
|
| 634 |
+
"policy_rollout_progress": 0.518719785640725,
|
| 635 |
+
"policy_rollout_success_rate": 0.12389380530973451,
|
| 636 |
+
"restore_max_error": 4.76837158203125e-07
|
| 637 |
+
},
|
| 638 |
+
"PickCube-v1": {
|
| 639 |
+
"action_mse_to_best": 0.39618182427290344,
|
| 640 |
+
"expert_success_rate": 0.9402173913043478,
|
| 641 |
+
"num_groups": 184,
|
| 642 |
+
"oracle_success_rate": 0.9456521739130435,
|
| 643 |
+
"policy_expert_regret": 1.211850641467406,
|
| 644 |
+
"policy_oracle_regret": 1.2193875464347557,
|
| 645 |
+
"policy_rollout_progress": 0.5238371952133172,
|
| 646 |
+
"policy_rollout_success_rate": 0.1956521739130435,
|
| 647 |
+
"restore_max_error": 4.76837158203125e-07
|
| 648 |
+
},
|
| 649 |
+
"PullCube-v1": {
|
| 650 |
+
"action_mse_to_best": 0.747883105589273,
|
| 651 |
+
"expert_success_rate": 0.25,
|
| 652 |
+
"num_groups": 76,
|
| 653 |
+
"oracle_success_rate": 0.40789473684210525,
|
| 654 |
+
"policy_expert_regret": 0.35917731865897384,
|
| 655 |
+
"policy_oracle_regret": 0.522642692808356,
|
| 656 |
+
"policy_rollout_progress": 0.29850233055798236,
|
| 657 |
+
"policy_rollout_success_rate": 0.15789473684210525,
|
| 658 |
+
"restore_max_error": 4.76837158203125e-07
|
| 659 |
+
},
|
| 660 |
+
"PushCube-v1": {
|
| 661 |
+
"action_mse_to_best": 0.43588705656227766,
|
| 662 |
+
"expert_success_rate": 0.8198198198198198,
|
| 663 |
+
"num_groups": 111,
|
| 664 |
+
"oracle_success_rate": 1.0,
|
| 665 |
+
"policy_expert_regret": 0.4817217659574371,
|
| 666 |
+
"policy_oracle_regret": 0.5493626955661688,
|
| 667 |
+
"policy_rollout_progress": 0.7389255927221196,
|
| 668 |
+
"policy_rollout_success_rate": 0.7117117117117117,
|
| 669 |
+
"restore_max_error": 4.76837158203125e-07
|
| 670 |
+
},
|
| 671 |
+
"StackCube-v1": {
|
| 672 |
+
"action_mse_to_best": 0.6367085376283624,
|
| 673 |
+
"expert_success_rate": 0.6923076923076923,
|
| 674 |
+
"num_groups": 91,
|
| 675 |
+
"oracle_success_rate": 0.8571428571428571,
|
| 676 |
+
"policy_expert_regret": 1.1808721947145986,
|
| 677 |
+
"policy_oracle_regret": 1.3586157239400423,
|
| 678 |
+
"policy_rollout_progress": 0.31947578620779643,
|
| 679 |
+
"policy_rollout_success_rate": 0.15384615384615385,
|
| 680 |
+
"restore_max_error": 3.948807716369629e-07
|
| 681 |
+
}
|
| 682 |
+
}
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"config": "k64_sigma0.50",
|
| 686 |
+
"seed": 2,
|
| 687 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k64_sigma0.50/seed_2/online_rollout.json",
|
| 688 |
+
"selection_mode": "field",
|
| 689 |
+
"num_candidates": 64,
|
| 690 |
+
"candidate_sigma": 0.5,
|
| 691 |
+
"field_optim_steps": 0,
|
| 692 |
+
"field_optim_step_size": 0.0,
|
| 693 |
+
"field_optim_trust_radius": 0.0,
|
| 694 |
+
"field_optim_l2_penalty": 0.0,
|
| 695 |
+
"retrieval_neighbors": 0,
|
| 696 |
+
"num_groups": 575,
|
| 697 |
+
"policy_rollout_success_rate": 0.28347826086956524,
|
| 698 |
+
"policy_rollout_progress": 0.5176484204051287,
|
| 699 |
+
"oracle_success_rate": 0.8765217391304347,
|
| 700 |
+
"action_mse_to_best": 0.5004424169724402,
|
| 701 |
+
"per_task": {
|
| 702 |
+
"LiftPegUpright-v1": {
|
| 703 |
+
"action_mse_to_best": 0.4013568146813971,
|
| 704 |
+
"expert_success_rate": 0.8229166666666666,
|
| 705 |
+
"num_groups": 96,
|
| 706 |
+
"oracle_success_rate": 0.9270833333333334,
|
| 707 |
+
"policy_expert_regret": 0.9720403482206166,
|
| 708 |
+
"policy_oracle_regret": 1.065440983666728,
|
| 709 |
+
"policy_rollout_progress": 0.6228157593868673,
|
| 710 |
+
"policy_rollout_success_rate": 0.21875,
|
| 711 |
+
"restore_max_error": 3.5762786865234375e-07
|
| 712 |
+
},
|
| 713 |
+
"PickCube-v1": {
|
| 714 |
+
"action_mse_to_best": 0.3729282287749076,
|
| 715 |
+
"expert_success_rate": 0.9444444444444444,
|
| 716 |
+
"num_groups": 198,
|
| 717 |
+
"oracle_success_rate": 0.9595959595959596,
|
| 718 |
+
"policy_expert_regret": 1.1722496731131515,
|
| 719 |
+
"policy_oracle_regret": 1.17933312364186,
|
| 720 |
+
"policy_rollout_progress": 0.5412212638372574,
|
| 721 |
+
"policy_rollout_success_rate": 0.22727272727272727,
|
| 722 |
+
"restore_max_error": 4.76837158203125e-07
|
| 723 |
+
},
|
| 724 |
+
"PullCube-v1": {
|
| 725 |
+
"action_mse_to_best": 0.8188039211142394,
|
| 726 |
+
"expert_success_rate": 0.24444444444444444,
|
| 727 |
+
"num_groups": 90,
|
| 728 |
+
"oracle_success_rate": 0.4666666666666667,
|
| 729 |
+
"policy_expert_regret": 0.3964810552903347,
|
| 730 |
+
"policy_oracle_regret": 0.6969465435586042,
|
| 731 |
+
"policy_rollout_progress": 0.2539229686682423,
|
| 732 |
+
"policy_rollout_success_rate": 0.12222222222222222,
|
| 733 |
+
"restore_max_error": 4.0978193283081055e-07
|
| 734 |
+
},
|
| 735 |
+
"PushCube-v1": {
|
| 736 |
+
"action_mse_to_best": 0.4307129751927782,
|
| 737 |
+
"expert_success_rate": 0.8514851485148515,
|
| 738 |
+
"num_groups": 101,
|
| 739 |
+
"oracle_success_rate": 1.0,
|
| 740 |
+
"policy_expert_regret": 0.37918733148881706,
|
| 741 |
+
"policy_oracle_regret": 0.4173543913529651,
|
| 742 |
+
"policy_rollout_progress": 0.8004673908252528,
|
| 743 |
+
"policy_rollout_success_rate": 0.7821782178217822,
|
| 744 |
+
"restore_max_error": 4.76837158203125e-07
|
| 745 |
+
},
|
| 746 |
+
"StackCube-v1": {
|
| 747 |
+
"action_mse_to_best": 0.6465553650839462,
|
| 748 |
+
"expert_success_rate": 0.7666666666666667,
|
| 749 |
+
"num_groups": 90,
|
| 750 |
+
"oracle_success_rate": 0.9111111111111111,
|
| 751 |
+
"policy_expert_regret": 1.3943355371554693,
|
| 752 |
+
"policy_oracle_regret": 1.5042877657545937,
|
| 753 |
+
"policy_rollout_progress": 0.2999493882060051,
|
| 754 |
+
"policy_rollout_success_rate": 0.07777777777777778,
|
| 755 |
+
"restore_max_error": 4.76837158203125e-07
|
| 756 |
+
}
|
| 757 |
+
}
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"config": "k8_sigma0.10",
|
| 761 |
+
"seed": 0,
|
| 762 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k8_sigma0.10/seed_0/online_rollout.json",
|
| 763 |
+
"selection_mode": "field",
|
| 764 |
+
"num_candidates": 8,
|
| 765 |
+
"candidate_sigma": 0.1,
|
| 766 |
+
"field_optim_steps": 0,
|
| 767 |
+
"field_optim_step_size": 0.0,
|
| 768 |
+
"field_optim_trust_radius": 0.0,
|
| 769 |
+
"field_optim_l2_penalty": 0.0,
|
| 770 |
+
"retrieval_neighbors": 0,
|
| 771 |
+
"num_groups": 575,
|
| 772 |
+
"policy_rollout_success_rate": 0.24521739130434783,
|
| 773 |
+
"policy_rollout_progress": 0.4916666813407336,
|
| 774 |
+
"oracle_success_rate": 0.8573913043478261,
|
| 775 |
+
"action_mse_to_best": 0.4524545120091542,
|
| 776 |
+
"per_task": {
|
| 777 |
+
"LiftPegUpright-v1": {
|
| 778 |
+
"action_mse_to_best": 0.36152367228546095,
|
| 779 |
+
"expert_success_rate": 0.8865979381443299,
|
| 780 |
+
"num_groups": 97,
|
| 781 |
+
"oracle_success_rate": 0.9278350515463918,
|
| 782 |
+
"policy_expert_regret": 1.1890621543237843,
|
| 783 |
+
"policy_oracle_regret": 1.228676609925388,
|
| 784 |
+
"policy_rollout_progress": 0.5431373600185532,
|
| 785 |
+
"policy_rollout_success_rate": 0.14432989690721648,
|
| 786 |
+
"restore_max_error": 4.76837158203125e-07
|
| 787 |
+
},
|
| 788 |
+
"PickCube-v1": {
|
| 789 |
+
"action_mse_to_best": 0.3476500255593027,
|
| 790 |
+
"expert_success_rate": 0.9375,
|
| 791 |
+
"num_groups": 208,
|
| 792 |
+
"oracle_success_rate": 0.9471153846153846,
|
| 793 |
+
"policy_expert_regret": 1.2102034536728752,
|
| 794 |
+
"policy_oracle_regret": 1.2168700277269147,
|
| 795 |
+
"policy_rollout_progress": 0.5209172252815244,
|
| 796 |
+
"policy_rollout_success_rate": 0.1875,
|
| 797 |
+
"restore_max_error": 4.76837158203125e-07
|
| 798 |
+
},
|
| 799 |
+
"PullCube-v1": {
|
| 800 |
+
"action_mse_to_best": 0.7061071962892235,
|
| 801 |
+
"expert_success_rate": 0.19480519480519481,
|
| 802 |
+
"num_groups": 77,
|
| 803 |
+
"oracle_success_rate": 0.36363636363636365,
|
| 804 |
+
"policy_expert_regret": 0.23013423346043504,
|
| 805 |
+
"policy_oracle_regret": 0.47666968106800184,
|
| 806 |
+
"policy_rollout_progress": 0.3158751792764267,
|
| 807 |
+
"policy_rollout_success_rate": 0.16883116883116883,
|
| 808 |
+
"restore_max_error": 4.76837158203125e-07
|
| 809 |
+
},
|
| 810 |
+
"PushCube-v1": {
|
| 811 |
+
"action_mse_to_best": 0.45377475356167934,
|
| 812 |
+
"expert_success_rate": 0.8617021276595744,
|
| 813 |
+
"num_groups": 94,
|
| 814 |
+
"oracle_success_rate": 0.9893617021276596,
|
| 815 |
+
"policy_expert_regret": 0.5378522131037204,
|
| 816 |
+
"policy_oracle_regret": 0.6176136973056388,
|
| 817 |
+
"policy_rollout_progress": 0.701535238864574,
|
| 818 |
+
"policy_rollout_success_rate": 0.6808510638297872,
|
| 819 |
+
"restore_max_error": 4.76837158203125e-07
|
| 820 |
+
},
|
| 821 |
+
"StackCube-v1": {
|
| 822 |
+
"action_mse_to_best": 0.5632046659411204,
|
| 823 |
+
"expert_success_rate": 0.6767676767676768,
|
| 824 |
+
"num_groups": 99,
|
| 825 |
+
"oracle_success_rate": 0.8585858585858586,
|
| 826 |
+
"policy_expert_regret": 1.1949022051059839,
|
| 827 |
+
"policy_oracle_regret": 1.3925609213836265,
|
| 828 |
+
"policy_rollout_progress": 0.31723771447485144,
|
| 829 |
+
"policy_rollout_success_rate": 0.1111111111111111,
|
| 830 |
+
"restore_max_error": 3.948807716369629e-07
|
| 831 |
+
}
|
| 832 |
+
}
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"config": "k8_sigma0.10",
|
| 836 |
+
"seed": 1,
|
| 837 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k8_sigma0.10/seed_1/online_rollout.json",
|
| 838 |
+
"selection_mode": "field",
|
| 839 |
+
"num_candidates": 8,
|
| 840 |
+
"candidate_sigma": 0.1,
|
| 841 |
+
"field_optim_steps": 0,
|
| 842 |
+
"field_optim_step_size": 0.0,
|
| 843 |
+
"field_optim_trust_radius": 0.0,
|
| 844 |
+
"field_optim_l2_penalty": 0.0,
|
| 845 |
+
"retrieval_neighbors": 0,
|
| 846 |
+
"num_groups": 575,
|
| 847 |
+
"policy_rollout_success_rate": 0.26260869565217393,
|
| 848 |
+
"policy_rollout_progress": 0.5003497520121544,
|
| 849 |
+
"oracle_success_rate": 0.8695652173913043,
|
| 850 |
+
"action_mse_to_best": 0.46732707200005,
|
| 851 |
+
"per_task": {
|
| 852 |
+
"LiftPegUpright-v1": {
|
| 853 |
+
"action_mse_to_best": 0.3871589671836886,
|
| 854 |
+
"expert_success_rate": 0.8584070796460177,
|
| 855 |
+
"num_groups": 113,
|
| 856 |
+
"oracle_success_rate": 0.9380530973451328,
|
| 857 |
+
"policy_expert_regret": 1.1937605795343365,
|
| 858 |
+
"policy_oracle_regret": 1.2726808705952315,
|
| 859 |
+
"policy_rollout_progress": 0.5155556234901986,
|
| 860 |
+
"policy_rollout_success_rate": 0.13274336283185842,
|
| 861 |
+
"restore_max_error": 4.76837158203125e-07
|
| 862 |
+
},
|
| 863 |
+
"PickCube-v1": {
|
| 864 |
+
"action_mse_to_best": 0.3765532473385658,
|
| 865 |
+
"expert_success_rate": 0.9402173913043478,
|
| 866 |
+
"num_groups": 184,
|
| 867 |
+
"oracle_success_rate": 0.9456521739130435,
|
| 868 |
+
"policy_expert_regret": 1.2052235437111687,
|
| 869 |
+
"policy_oracle_regret": 1.2127604486785182,
|
| 870 |
+
"policy_rollout_progress": 0.5304642929695547,
|
| 871 |
+
"policy_rollout_success_rate": 0.1956521739130435,
|
| 872 |
+
"restore_max_error": 4.76837158203125e-07
|
| 873 |
+
},
|
| 874 |
+
"PullCube-v1": {
|
| 875 |
+
"action_mse_to_best": 0.6689964332127649,
|
| 876 |
+
"expert_success_rate": 0.25,
|
| 877 |
+
"num_groups": 76,
|
| 878 |
+
"oracle_success_rate": 0.40789473684210525,
|
| 879 |
+
"policy_expert_regret": 0.387804974581262,
|
| 880 |
+
"policy_oracle_regret": 0.6173880723010945,
|
| 881 |
+
"policy_rollout_progress": 0.2620575173856004,
|
| 882 |
+
"policy_rollout_success_rate": 0.10526315789473684,
|
| 883 |
+
"restore_max_error": 4.76837158203125e-07
|
| 884 |
+
},
|
| 885 |
+
"PushCube-v1": {
|
| 886 |
+
"action_mse_to_best": 0.42434008553758396,
|
| 887 |
+
"expert_success_rate": 0.8198198198198198,
|
| 888 |
+
"num_groups": 111,
|
| 889 |
+
"oracle_success_rate": 1.0,
|
| 890 |
+
"policy_expert_regret": 0.44538252471803547,
|
| 891 |
+
"policy_oracle_regret": 0.52979050294773,
|
| 892 |
+
"policy_rollout_progress": 0.7494887763315493,
|
| 893 |
+
"policy_rollout_success_rate": 0.7207207207207207,
|
| 894 |
+
"restore_max_error": 4.76837158203125e-07
|
| 895 |
+
},
|
| 896 |
+
"StackCube-v1": {
|
| 897 |
+
"action_mse_to_best": 0.6344266722981746,
|
| 898 |
+
"expert_success_rate": 0.6923076923076923,
|
| 899 |
+
"num_groups": 91,
|
| 900 |
+
"oracle_success_rate": 0.8571428571428571,
|
| 901 |
+
"policy_expert_regret": 1.2066307660642561,
|
| 902 |
+
"policy_oracle_regret": 1.3843742952896998,
|
| 903 |
+
"policy_rollout_progress": 0.3156952368361609,
|
| 904 |
+
"policy_rollout_success_rate": 0.13186813186813187,
|
| 905 |
+
"restore_max_error": 3.948807716369629e-07
|
| 906 |
+
}
|
| 907 |
+
}
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"config": "k8_sigma0.10",
|
| 911 |
+
"seed": 2,
|
| 912 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep/k8_sigma0.10/seed_2/online_rollout.json",
|
| 913 |
+
"selection_mode": "field",
|
| 914 |
+
"num_candidates": 8,
|
| 915 |
+
"candidate_sigma": 0.1,
|
| 916 |
+
"field_optim_steps": 0,
|
| 917 |
+
"field_optim_step_size": 0.0,
|
| 918 |
+
"field_optim_trust_radius": 0.0,
|
| 919 |
+
"field_optim_l2_penalty": 0.0,
|
| 920 |
+
"retrieval_neighbors": 0,
|
| 921 |
+
"num_groups": 575,
|
| 922 |
+
"policy_rollout_success_rate": 0.2817391304347826,
|
| 923 |
+
"policy_rollout_progress": 0.5176694101440776,
|
| 924 |
+
"oracle_success_rate": 0.8765217391304347,
|
| 925 |
+
"action_mse_to_best": 0.4807908735229917,
|
| 926 |
+
"per_task": {
|
| 927 |
+
"LiftPegUpright-v1": {
|
| 928 |
+
"action_mse_to_best": 0.39125924691325054,
|
| 929 |
+
"expert_success_rate": 0.8229166666666666,
|
| 930 |
+
"num_groups": 96,
|
| 931 |
+
"oracle_success_rate": 0.9270833333333334,
|
| 932 |
+
"policy_expert_regret": 1.0079390796211858,
|
| 933 |
+
"policy_oracle_regret": 1.0878960588015616,
|
| 934 |
+
"policy_rollout_progress": 0.624040465336293,
|
| 935 |
+
"policy_rollout_success_rate": 0.20833333333333334,
|
| 936 |
+
"restore_max_error": 3.5762786865234375e-07
|
| 937 |
+
},
|
| 938 |
+
"PickCube-v1": {
|
| 939 |
+
"action_mse_to_best": 0.36567344943607094,
|
| 940 |
+
"expert_success_rate": 0.9444444444444444,
|
| 941 |
+
"num_groups": 198,
|
| 942 |
+
"oracle_success_rate": 0.9595959595959596,
|
| 943 |
+
"policy_expert_regret": 1.170388219614673,
|
| 944 |
+
"policy_oracle_regret": 1.1774716701433816,
|
| 945 |
+
"policy_rollout_progress": 0.5430827173357359,
|
| 946 |
+
"policy_rollout_success_rate": 0.22727272727272727,
|
| 947 |
+
"restore_max_error": 4.76837158203125e-07
|
| 948 |
+
},
|
| 949 |
+
"PullCube-v1": {
|
| 950 |
+
"action_mse_to_best": 0.7307745517128044,
|
| 951 |
+
"expert_success_rate": 0.24444444444444444,
|
| 952 |
+
"num_groups": 90,
|
| 953 |
+
"oracle_success_rate": 0.4666666666666667,
|
| 954 |
+
"policy_expert_regret": 0.38108951423176524,
|
| 955 |
+
"policy_oracle_regret": 0.6361748364926219,
|
| 956 |
+
"policy_rollout_progress": 0.28386651941198376,
|
| 957 |
+
"policy_rollout_success_rate": 0.15555555555555556,
|
| 958 |
+
"restore_max_error": 4.0978193283081055e-07
|
| 959 |
+
},
|
| 960 |
+
"PushCube-v1": {
|
| 961 |
+
"action_mse_to_best": 0.4313800072315896,
|
| 962 |
+
"expert_success_rate": 0.8514851485148515,
|
| 963 |
+
"num_groups": 101,
|
| 964 |
+
"oracle_success_rate": 1.0,
|
| 965 |
+
"policy_expert_regret": 0.43261517717106507,
|
| 966 |
+
"policy_oracle_regret": 0.47078223703521316,
|
| 967 |
+
"policy_rollout_progress": 0.7767425154400344,
|
| 968 |
+
"policy_rollout_success_rate": 0.7524752475247525,
|
| 969 |
+
"restore_max_error": 4.76837158203125e-07
|
| 970 |
+
},
|
| 971 |
+
"StackCube-v1": {
|
| 972 |
+
"action_mse_to_best": 0.6350159022129245,
|
| 973 |
+
"expert_success_rate": 0.7666666666666667,
|
| 974 |
+
"num_groups": 90,
|
| 975 |
+
"oracle_success_rate": 0.9111111111111111,
|
| 976 |
+
"policy_expert_regret": 1.402921955121888,
|
| 977 |
+
"policy_oracle_regret": 1.5128741837210125,
|
| 978 |
+
"policy_rollout_progress": 0.2913629702395863,
|
| 979 |
+
"policy_rollout_success_rate": 0.07777777777777778,
|
| 980 |
+
"restore_max_error": 4.76837158203125e-07
|
| 981 |
+
}
|
| 982 |
+
}
|
| 983 |
+
}
|
| 984 |
+
]
|
| 985 |
+
}
|
results/h16_policy_ckpt_nonexpert_policy_bc5_bestpt_field_sweep_summary.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# h=16 Field-Guided Rollout Sweep
|
| 2 |
+
|
| 3 |
+
Result root: `/scratch/knguy52/dovla/experiments/dovla_h16_nonexpert_policy_bc5_bestpt_field_sweep`
|
| 4 |
+
Completed result files: 12
|
| 5 |
+
Baseline h=4 policy success: 29.67%
|
| 6 |
+
Baseline h=16 policy success: 29.74%
|
| 7 |
+
|
| 8 |
+
| config | seeds | mean success | gain vs h=16 | progress | action MSE |
|
| 9 |
+
|---|---:|---:|---:|---:|---:|
|
| 10 |
+
| k64_sigma0.50 | 3 | 26.49% | -3.25% | 50.23% | 0.484 |
|
| 11 |
+
| k8_sigma0.10 | 3 | 26.32% | -3.42% | 50.32% | 0.467 |
|
| 12 |
+
| k32_sigma0.35 | 3 | 26.03% | -3.71% | 50.16% | 0.477 |
|
| 13 |
+
| k16_sigma0.20 | 3 | 25.62% | -4.12% | 49.59% | 0.471 |
|
| 14 |
+
|
| 15 |
+
Best config:
|
| 16 |
+
- k64_sigma0.50
|
| 17 |
+
- mean success: 26.49%
|
| 18 |
+
- gain vs h=16 policy: -3.25%
|
results/h16_policy_ckpt_nonexpert_policy_bc5_summary.json
ADDED
|
@@ -0,0 +1,277 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run_root": "/scratch/knguy52/dovla/experiments/dovla_h16_policy_ckpt_runs",
|
| 3 |
+
"objective": "nonexpert_policy_bc5",
|
| 4 |
+
"out_name": "policy_rollout.json",
|
| 5 |
+
"num_completed": 3,
|
| 6 |
+
"baseline_h4_policy_success": 0.2967,
|
| 7 |
+
"baseline_h16_rank_checkpoint_success": 0.29739130434782607,
|
| 8 |
+
"mean_success": 0.2788405797101449,
|
| 9 |
+
"std_success": 0.03624463543731149,
|
| 10 |
+
"mean_progress": 0.4986166725033705,
|
| 11 |
+
"mean_action_mse_to_best": 0.46685135011925644,
|
| 12 |
+
"gain_vs_h4": -0.0178594202898551,
|
| 13 |
+
"gain_vs_h16_rank_checkpoint": -0.01855072463768115,
|
| 14 |
+
"rows": [
|
| 15 |
+
{
|
| 16 |
+
"seed": 0,
|
| 17 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_policy_ckpt_runs/nonexpert_policy_bc5/seed_0/policy_rollout.json",
|
| 18 |
+
"num_groups": 575,
|
| 19 |
+
"selection_mode": "policy",
|
| 20 |
+
"num_candidates": 1,
|
| 21 |
+
"candidate_sigma": 0.0,
|
| 22 |
+
"field_optim_steps": 0,
|
| 23 |
+
"field_optim_step_size": 0.0,
|
| 24 |
+
"field_optim_trust_radius": 0.0,
|
| 25 |
+
"field_optim_l2_penalty": 0.0,
|
| 26 |
+
"retrieval_neighbors": 0,
|
| 27 |
+
"policy_rollout_success_rate": 0.271304347826087,
|
| 28 |
+
"policy_rollout_progress": 0.5057818350033916,
|
| 29 |
+
"oracle_success_rate": 0.8573913043478261,
|
| 30 |
+
"action_mse_to_best": 0.4584467859323258,
|
| 31 |
+
"best_policy_val": {
|
| 32 |
+
"bc_loss": 0.22882285051875645,
|
| 33 |
+
"field_effect_loss": 0.009925915497458644,
|
| 34 |
+
"field_potential_loss": 0.26158512383699417,
|
| 35 |
+
"field_preference_loss": 0.5015371458397971,
|
| 36 |
+
"lattice_edges": 3833.3333333333335,
|
| 37 |
+
"progress_mae": 0.183095068567329,
|
| 38 |
+
"rank_acc": 0.8338018423981137,
|
| 39 |
+
"rank_loss": 0.5015179067850113,
|
| 40 |
+
"regret_mae": 0.39475825760099625,
|
| 41 |
+
"success_accuracy": 0.8829070031642914,
|
| 42 |
+
"total_loss": 1.996809138192071
|
| 43 |
+
},
|
| 44 |
+
"per_task": {
|
| 45 |
+
"LiftPegUpright-v1": {
|
| 46 |
+
"action_mse_to_best": 0.3718961723840114,
|
| 47 |
+
"expert_success_rate": 0.8865979381443299,
|
| 48 |
+
"num_groups": 97,
|
| 49 |
+
"oracle_success_rate": 0.9278350515463918,
|
| 50 |
+
"policy_expert_regret": 1.1706991556686224,
|
| 51 |
+
"policy_oracle_regret": 1.210225482423281,
|
| 52 |
+
"policy_rollout_progress": 0.538151837347709,
|
| 53 |
+
"policy_rollout_success_rate": 0.15463917525773196,
|
| 54 |
+
"restore_max_error": 4.76837158203125e-07
|
| 55 |
+
},
|
| 56 |
+
"PickCube-v1": {
|
| 57 |
+
"action_mse_to_best": 0.37033563929323393,
|
| 58 |
+
"expert_success_rate": 0.9375,
|
| 59 |
+
"num_groups": 208,
|
| 60 |
+
"oracle_success_rate": 0.9471153846153846,
|
| 61 |
+
"policy_expert_regret": 1.1347902767772142,
|
| 62 |
+
"policy_oracle_regret": 1.134811511505037,
|
| 63 |
+
"policy_rollout_progress": 0.5520318459020928,
|
| 64 |
+
"policy_rollout_success_rate": 0.24519230769230768,
|
| 65 |
+
"restore_max_error": 4.76837158203125e-07
|
| 66 |
+
},
|
| 67 |
+
"PullCube-v1": {
|
| 68 |
+
"action_mse_to_best": 0.6628895942000793,
|
| 69 |
+
"expert_success_rate": 0.19480519480519481,
|
| 70 |
+
"num_groups": 77,
|
| 71 |
+
"oracle_success_rate": 0.36363636363636365,
|
| 72 |
+
"policy_expert_regret": 0.35412532395937224,
|
| 73 |
+
"policy_oracle_regret": 0.5143780756209578,
|
| 74 |
+
"policy_rollout_progress": 0.2621346838385254,
|
| 75 |
+
"policy_rollout_success_rate": 0.11688311688311688,
|
| 76 |
+
"restore_max_error": 4.76837158203125e-07
|
| 77 |
+
},
|
| 78 |
+
"PushCube-v1": {
|
| 79 |
+
"action_mse_to_best": 0.4131437000679843,
|
| 80 |
+
"expert_success_rate": 0.8617021276595744,
|
| 81 |
+
"num_groups": 94,
|
| 82 |
+
"oracle_success_rate": 0.9893617021276596,
|
| 83 |
+
"policy_expert_regret": 0.4141900946802281,
|
| 84 |
+
"policy_oracle_regret": 0.4922155891644194,
|
| 85 |
+
"policy_rollout_progress": 0.7541142459562484,
|
| 86 |
+
"policy_rollout_success_rate": 0.7340425531914894,
|
| 87 |
+
"restore_max_error": 4.76837158203125e-07
|
| 88 |
+
},
|
| 89 |
+
"StackCube-v1": {
|
| 90 |
+
"action_mse_to_best": 0.6123752894651409,
|
| 91 |
+
"expert_success_rate": 0.6767676767676768,
|
| 92 |
+
"num_groups": 99,
|
| 93 |
+
"oracle_success_rate": 0.8585858585858586,
|
| 94 |
+
"policy_expert_regret": 1.1471272556468695,
|
| 95 |
+
"policy_oracle_regret": 1.3690906239278389,
|
| 96 |
+
"policy_rollout_progress": 0.330607001829629,
|
| 97 |
+
"policy_rollout_success_rate": 0.12121212121212122,
|
| 98 |
+
"restore_max_error": 3.948807716369629e-07
|
| 99 |
+
}
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"seed": 1,
|
| 104 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_policy_ckpt_runs/nonexpert_policy_bc5/seed_1/policy_rollout.json",
|
| 105 |
+
"num_groups": 575,
|
| 106 |
+
"selection_mode": "policy",
|
| 107 |
+
"num_candidates": 1,
|
| 108 |
+
"candidate_sigma": 0.0,
|
| 109 |
+
"field_optim_steps": 0,
|
| 110 |
+
"field_optim_step_size": 0.0,
|
| 111 |
+
"field_optim_trust_radius": 0.0,
|
| 112 |
+
"field_optim_l2_penalty": 0.0,
|
| 113 |
+
"retrieval_neighbors": 0,
|
| 114 |
+
"policy_rollout_success_rate": 0.24695652173913044,
|
| 115 |
+
"policy_rollout_progress": 0.46983929049041445,
|
| 116 |
+
"oracle_success_rate": 0.8695652173913043,
|
| 117 |
+
"action_mse_to_best": 0.4556999360786184,
|
| 118 |
+
"best_policy_val": {
|
| 119 |
+
"bc_loss": 0.23992785231934655,
|
| 120 |
+
"field_effect_loss": 0.009765874206398925,
|
| 121 |
+
"field_potential_loss": 0.2597191996044583,
|
| 122 |
+
"field_preference_loss": 0.5161888053019842,
|
| 123 |
+
"lattice_edges": 3833.3333333333335,
|
| 124 |
+
"progress_mae": 0.1927904850906796,
|
| 125 |
+
"rank_acc": 0.8293034666114383,
|
| 126 |
+
"rank_loss": 0.5161840038167106,
|
| 127 |
+
"regret_mae": 0.3643288281228807,
|
| 128 |
+
"success_accuracy": 0.873417897356881,
|
| 129 |
+
"total_loss": 2.070632172955407
|
| 130 |
+
},
|
| 131 |
+
"per_task": {
|
| 132 |
+
"LiftPegUpright-v1": {
|
| 133 |
+
"action_mse_to_best": 0.37196040315042556,
|
| 134 |
+
"expert_success_rate": 0.8584070796460177,
|
| 135 |
+
"num_groups": 113,
|
| 136 |
+
"oracle_success_rate": 0.9380530973451328,
|
| 137 |
+
"policy_expert_regret": 1.231745108962059,
|
| 138 |
+
"policy_oracle_regret": 1.310917024459459,
|
| 139 |
+
"policy_rollout_progress": 0.47727092348896294,
|
| 140 |
+
"policy_rollout_success_rate": 0.13274336283185842,
|
| 141 |
+
"restore_max_error": 4.76837158203125e-07
|
| 142 |
+
},
|
| 143 |
+
"PickCube-v1": {
|
| 144 |
+
"action_mse_to_best": 0.3537537027352854,
|
| 145 |
+
"expert_success_rate": 0.9402173913043478,
|
| 146 |
+
"num_groups": 184,
|
| 147 |
+
"oracle_success_rate": 0.9456521739130435,
|
| 148 |
+
"policy_expert_regret": 1.1557285721602333,
|
| 149 |
+
"policy_oracle_regret": 1.1632654771275828,
|
| 150 |
+
"policy_rollout_progress": 0.547350568868316,
|
| 151 |
+
"policy_rollout_success_rate": 0.22826086956521738,
|
| 152 |
+
"restore_max_error": 4.76837158203125e-07
|
| 153 |
+
},
|
| 154 |
+
"PullCube-v1": {
|
| 155 |
+
"action_mse_to_best": 0.664808021331402,
|
| 156 |
+
"expert_success_rate": 0.25,
|
| 157 |
+
"num_groups": 76,
|
| 158 |
+
"oracle_success_rate": 0.40789473684210525,
|
| 159 |
+
"policy_expert_regret": 0.3675110892784831,
|
| 160 |
+
"policy_oracle_regret": 0.645981286088691,
|
| 161 |
+
"policy_rollout_progress": 0.2525524773733004,
|
| 162 |
+
"policy_rollout_success_rate": 0.10526315789473684,
|
| 163 |
+
"restore_max_error": 4.76837158203125e-07
|
| 164 |
+
},
|
| 165 |
+
"PushCube-v1": {
|
| 166 |
+
"action_mse_to_best": 0.41876735199276394,
|
| 167 |
+
"expert_success_rate": 0.8198198198198198,
|
| 168 |
+
"num_groups": 111,
|
| 169 |
+
"oracle_success_rate": 1.0,
|
| 170 |
+
"policy_expert_regret": 0.7343031088779638,
|
| 171 |
+
"policy_oracle_regret": 0.8522085335340586,
|
| 172 |
+
"policy_rollout_progress": 0.5892329079073828,
|
| 173 |
+
"policy_rollout_success_rate": 0.5585585585585585,
|
| 174 |
+
"restore_max_error": 4.76837158203125e-07
|
| 175 |
+
},
|
| 176 |
+
"StackCube-v1": {
|
| 177 |
+
"action_mse_to_best": 0.6362271504783696,
|
| 178 |
+
"expert_success_rate": 0.6923076923076923,
|
| 179 |
+
"num_groups": 91,
|
| 180 |
+
"oracle_success_rate": 0.8571428571428571,
|
| 181 |
+
"policy_expert_regret": 1.142687132725349,
|
| 182 |
+
"policy_oracle_regret": 1.3147745053846758,
|
| 183 |
+
"policy_rollout_progress": 0.3397212301964288,
|
| 184 |
+
"policy_rollout_success_rate": 0.16483516483516483,
|
| 185 |
+
"restore_max_error": 3.948807716369629e-07
|
| 186 |
+
}
|
| 187 |
+
}
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"seed": 2,
|
| 191 |
+
"path": "/scratch/knguy52/dovla/experiments/dovla_h16_policy_ckpt_runs/nonexpert_policy_bc5/seed_2/policy_rollout.json",
|
| 192 |
+
"num_groups": 575,
|
| 193 |
+
"selection_mode": "policy",
|
| 194 |
+
"num_candidates": 1,
|
| 195 |
+
"candidate_sigma": 0.0,
|
| 196 |
+
"field_optim_steps": 0,
|
| 197 |
+
"field_optim_step_size": 0.0,
|
| 198 |
+
"field_optim_trust_radius": 0.0,
|
| 199 |
+
"field_optim_l2_penalty": 0.0,
|
| 200 |
+
"retrieval_neighbors": 0,
|
| 201 |
+
"policy_rollout_success_rate": 0.3182608695652174,
|
| 202 |
+
"policy_rollout_progress": 0.5202288920163055,
|
| 203 |
+
"oracle_success_rate": 0.8765217391304347,
|
| 204 |
+
"action_mse_to_best": 0.48640732834682515,
|
| 205 |
+
"best_policy_val": {
|
| 206 |
+
"bc_loss": 0.22642304665512508,
|
| 207 |
+
"field_effect_loss": 0.009216919282658232,
|
| 208 |
+
"field_potential_loss": 0.2535000989834468,
|
| 209 |
+
"field_preference_loss": 0.5141381952497694,
|
| 210 |
+
"lattice_edges": 3833.3333333333335,
|
| 211 |
+
"progress_mae": 0.19063449651002884,
|
| 212 |
+
"rank_acc": 0.8354685604572296,
|
| 213 |
+
"rank_loss": 0.5141238040394254,
|
| 214 |
+
"regret_mae": 0.3577662805716197,
|
| 215 |
+
"success_accuracy": 0.8673030071788363,
|
| 216 |
+
"total_loss": 1.9934748278723822
|
| 217 |
+
},
|
| 218 |
+
"per_task": {
|
| 219 |
+
"LiftPegUpright-v1": {
|
| 220 |
+
"action_mse_to_best": 0.39389084130137536,
|
| 221 |
+
"expert_success_rate": 0.8229166666666666,
|
| 222 |
+
"num_groups": 96,
|
| 223 |
+
"oracle_success_rate": 0.9270833333333334,
|
| 224 |
+
"policy_expert_regret": 1.097471557247142,
|
| 225 |
+
"policy_oracle_regret": 1.2171342537427943,
|
| 226 |
+
"policy_rollout_progress": 0.5468856037283937,
|
| 227 |
+
"policy_rollout_success_rate": 0.15625,
|
| 228 |
+
"restore_max_error": 3.5762786865234375e-07
|
| 229 |
+
},
|
| 230 |
+
"PickCube-v1": {
|
| 231 |
+
"action_mse_to_best": 0.4138951218037894,
|
| 232 |
+
"expert_success_rate": 0.9444444444444444,
|
| 233 |
+
"num_groups": 198,
|
| 234 |
+
"oracle_success_rate": 0.9595959595959596,
|
| 235 |
+
"policy_expert_regret": 1.0740318188086302,
|
| 236 |
+
"policy_oracle_regret": 1.0811152693373387,
|
| 237 |
+
"policy_rollout_progress": 0.5564312692167181,
|
| 238 |
+
"policy_rollout_success_rate": 0.30303030303030304,
|
| 239 |
+
"restore_max_error": 4.76837158203125e-07
|
| 240 |
+
},
|
| 241 |
+
"PullCube-v1": {
|
| 242 |
+
"action_mse_to_best": 0.6742079236751629,
|
| 243 |
+
"expert_success_rate": 0.24444444444444444,
|
| 244 |
+
"num_groups": 90,
|
| 245 |
+
"oracle_success_rate": 0.4666666666666667,
|
| 246 |
+
"policy_expert_regret": 0.43056668554975963,
|
| 247 |
+
"policy_oracle_regret": 0.6623760463734572,
|
| 248 |
+
"policy_rollout_progress": 0.2854344742721878,
|
| 249 |
+
"policy_rollout_success_rate": 0.16666666666666666,
|
| 250 |
+
"restore_max_error": 4.0978193283081055e-07
|
| 251 |
+
},
|
| 252 |
+
"PushCube-v1": {
|
| 253 |
+
"action_mse_to_best": 0.4255952728856908,
|
| 254 |
+
"expert_success_rate": 0.8514851485148515,
|
| 255 |
+
"num_groups": 101,
|
| 256 |
+
"oracle_success_rate": 1.0,
|
| 257 |
+
"policy_expert_regret": 0.4492038683135911,
|
| 258 |
+
"policy_oracle_regret": 0.521469724502894,
|
| 259 |
+
"policy_rollout_progress": 0.7557579982693833,
|
| 260 |
+
"policy_rollout_success_rate": 0.7227722772277227,
|
| 261 |
+
"restore_max_error": 4.76837158203125e-07
|
| 262 |
+
},
|
| 263 |
+
"StackCube-v1": {
|
| 264 |
+
"action_mse_to_best": 0.625062480279141,
|
| 265 |
+
"expert_success_rate": 0.7666666666666667,
|
| 266 |
+
"num_groups": 90,
|
| 267 |
+
"oracle_success_rate": 0.9111111111111111,
|
| 268 |
+
"policy_expert_regret": 1.1541064727637502,
|
| 269 |
+
"policy_oracle_regret": 1.290107189781136,
|
| 270 |
+
"policy_rollout_progress": 0.38262825707594555,
|
| 271 |
+
"policy_rollout_success_rate": 0.2222222222222222,
|
| 272 |
+
"restore_max_error": 4.76837158203125e-07
|
| 273 |
+
}
|
| 274 |
+
}
|
| 275 |
+
}
|
| 276 |
+
]
|
| 277 |
+
}
|
results/h16_policy_ckpt_nonexpert_policy_bc5_summary.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# h=16 Best-Policy Checkpoint Rollout
|
| 2 |
+
|
| 3 |
+
Run root: `/scratch/knguy52/dovla/experiments/dovla_h16_policy_ckpt_runs`
|
| 4 |
+
Objective: `nonexpert_policy_bc5`
|
| 5 |
+
Result file: `policy_rollout.json`
|
| 6 |
+
Completed seeds: 3
|
| 7 |
+
Baseline h=4 policy success: 29.67%
|
| 8 |
+
Baseline h=16 rank-checkpoint success: 29.74%
|
| 9 |
+
|
| 10 |
+
Mean success: 27.88% +/- 3.62%
|
| 11 |
+
Gain vs h=16 rank checkpoint: -1.86%
|
| 12 |
+
Mean progress: 49.86%
|
| 13 |
+
Mean action MSE to best: 0.467
|
| 14 |
+
|
| 15 |
+
| seed | mode | k | retrieval K | sigma | opt steps | trust | success | progress | oracle | action MSE |
|
| 16 |
+
|---:|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|
|
| 17 |
+
| 0 | policy | 1 | 0 | 0.00 | 0 | 0.00 | 27.13% | 50.58% | 85.74% | 0.458 |
|
| 18 |
+
| 1 | policy | 1 | 0 | 0.00 | 0 | 0.00 | 24.70% | 46.98% | 86.96% | 0.456 |
|
| 19 |
+
| 2 | policy | 1 | 0 | 0.00 | 0 | 0.00 | 31.83% | 52.02% | 87.65% | 0.486 |
|