ssuleiman/simrig-orbit-reach
043
1{2 "suite": "promotion",3 "passed": true,4 "scenario": "displayed",5 "episodes": 60,6 "successes": 54,7 "success_rate": 0.9,8 "safety_failures": 0,9 "failed_seeds": [10 9,11 10,12 13,13 16,14 18,15 4316 ],17 "failures": [18 {19 "seed": 9,20 "scenario": "displayed",21 "terminal_reason": {22 "category": "task_failure",23 "code": "target_not_sustained",24 "details": {25 "actual": 0,26 "expected": 5,27 "predicate_id": "sustained_target_arrival"28 },29 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."30 },31 "maximum_hold_steps": 0,32 "minimum_target_error": 0.24030554329234238,33 "forbidden_contact_count": 034 },35 {36 "seed": 10,37 "scenario": "displayed",38 "terminal_reason": {39 "category": "task_failure",40 "code": "target_not_sustained",41 "details": {42 "actual": 0,43 "expected": 5,44 "predicate_id": "sustained_target_arrival"45 },46 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."47 },48 "maximum_hold_steps": 0,49 "minimum_target_error": 0.22367826451961925,50 "forbidden_contact_count": 051 },52 {53 "seed": 13,54 "scenario": "displayed",55 "terminal_reason": {56 "category": "task_failure",57 "code": "target_not_sustained",58 "details": {59 "actual": 0,60 "expected": 5,61 "predicate_id": "sustained_target_arrival"62 },63 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."64 },65 "maximum_hold_steps": 0,66 "minimum_target_error": 0.10712519091374702,67 "forbidden_contact_count": 068 },69 {70 "seed": 16,71 "scenario": "displayed",72 "terminal_reason": {73 "category": "task_failure",74 "code": "target_not_sustained",75 "details": {76 "actual": 0,77 "expected": 5,78 "predicate_id": "sustained_target_arrival"79 },80 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."81 },82 "maximum_hold_steps": 0,83 "minimum_target_error": 0.0926555449924868,84 "forbidden_contact_count": 085 },86 {87 "seed": 18,88 "scenario": "displayed",89 "terminal_reason": {90 "category": "task_failure",91 "code": "target_not_sustained",92 "details": {93 "actual": 0,94 "expected": 5,95 "predicate_id": "sustained_target_arrival"96 },97 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."98 },99 "maximum_hold_steps": 0,100 "minimum_target_error": 0.1542196887033212,101 "forbidden_contact_count": 0102 },103 {104 "seed": 43,105 "scenario": "displayed",106 "terminal_reason": {107 "category": "task_failure",108 "code": "target_not_sustained",109 "details": {110 "actual": 0,111 "expected": 5,112 "predicate_id": "sustained_target_arrival"113 },114 "message": "Predicate 'sustained_target_arrival' failed: actual=0 expected=5."115 },116 "maximum_hold_steps": 0,117 "minimum_target_error": 0.10512675214180775,118 "forbidden_contact_count": 0119 }120 ],121 "trainer_eval_episode_success": 0.8125,122 "checkpoint_sha256": "8874731b50eca8b649df6b63b151526a8f2ba2dfd6276719e69858be9d2d26eb",123 "config_sha256": "f4c5ded83e7b696ef84e365067d560509b18095cca0ec9ed4357ce0309c56ae2"124}125 