{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8833975195884705, "min": 0.8833975195884705, "max": 2.8678886890411377, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8434.6796875, "min": 8434.6796875, "max": 29370.046875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.706733703613281, "min": 0.5055364370346069, "max": 12.706733703613281, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2477.81298828125, "min": 98.07406616210938, "max": 2579.436279296875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06999877664972753, "min": 0.06441057435782283, "max": 0.07514886251395664, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27999510659891014, "min": 0.2576422974312913, "max": 0.37519137562084526, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20428802146046768, "min": 0.15295373568968737, "max": 0.26598409519476046, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8171520858418707, "min": 0.6118149427587495, "max": 1.2996140399984284, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.977272727272727, "min": 4.2272727272727275, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1099.0, "min": 186.0, "max": 1387.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.977272727272727, "min": 4.2272727272727275, "max": 25.21818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1099.0, "min": 186.0, "max": 1387.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744936931", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /app/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744937249" }, "total": 317.3460517409999, "count": 1, "self": 0.4233881370000745, "children": { "run_training.setup": { "total": 0.04910299299990584, "count": 1, "self": 0.04910299299990584 }, "TrainerController.start_learning": { "total": 316.8735606109999, "count": 1, "self": 0.30364174297164936, "children": { "TrainerController._reset_env": { "total": 4.760540367999965, "count": 1, "self": 4.760540367999965 }, "TrainerController.advance": { "total": 311.7237928370282, "count": 18211, "self": 0.1388574910420175, "children": { "env_step": { "total": 311.5849353459862, "count": 18211, "self": 257.9774060360096, "children": { "SubprocessEnvManager._take_step": { "total": 53.47159700398515, "count": 18211, "self": 0.6446501190180243, "children": { "TorchPolicy.evaluate": { "total": 52.82694688496713, "count": 18211, "self": 52.82694688496713 } } }, "workers": { "total": 0.1359323059914459, "count": 18211, "self": 0.0, "children": { "worker_root": { "total": 316.2519637690125, "count": 18211, "is_parallel": true, "self": 104.38374902402802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012133920004089305, "count": 1, "is_parallel": true, "self": 0.0004040980006720929, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008092939997368376, "count": 10, "is_parallel": true, "self": 0.0008092939997368376 } } }, "UnityEnvironment.step": { "total": 0.021298900000147114, "count": 1, "is_parallel": true, "self": 0.0001663369994275854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015232000032483484, "count": 1, "is_parallel": true, "self": 0.00015232000032483484 }, "communicator.exchange": { "total": 0.020441687000129605, "count": 1, "is_parallel": true, "self": 0.020441687000129605 }, "steps_from_proto": { "total": 0.0005385560002650891, "count": 1, "is_parallel": true, "self": 0.00012639199985642335, "children": { "_process_rank_one_or_two_observation": { "total": 0.00041216400040866574, "count": 10, "is_parallel": true, "self": 0.00041216400040866574 } } } } } } }, "UnityEnvironment.step": { "total": 211.86821474498447, "count": 18210, "is_parallel": true, "self": 2.500489762998768, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6662476919864275, "count": 18210, "is_parallel": true, "self": 1.6662476919864275 }, "communicator.exchange": { "total": 200.37083707598458, "count": 18210, "is_parallel": true, "self": 200.37083707598458 }, "steps_from_proto": { "total": 7.330640214014693, "count": 18210, "is_parallel": true, "self": 1.690665224867189, "children": { "_process_rank_one_or_two_observation": { "total": 5.639974989147504, "count": 182100, "is_parallel": true, "self": 5.639974989147504 } } } } } } } } } } } } }, "trainer_threads": { "total": 9.013699991555768e-05, "count": 1, "self": 9.013699991555768e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 310.4482936108907, "count": 247914, "is_parallel": true, "self": 4.171879284842817, "children": { "process_trajectory": { "total": 184.80358216204968, "count": 247914, "is_parallel": true, "self": 184.11585616904995, "children": { "RLTrainer._checkpoint": { "total": 0.6877259929997308, "count": 4, "is_parallel": true, "self": 0.6877259929997308 } } }, "_update_policy": { "total": 121.47283216399819, "count": 90, "is_parallel": true, "self": 20.12624852900717, "children": { "TorchPPOOptimizer.update": { "total": 101.34658363499102, "count": 4587, "is_parallel": true, "self": 101.34658363499102 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08549552600015886, "count": 1, "self": 0.014681099999961589, "children": { "RLTrainer._checkpoint": { "total": 0.07081442600019727, "count": 1, "self": 0.07081442600019727 } } } } } } }