{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0280466079711914, "min": 1.0110224485397339, "max": 2.8750667572021484, "count": 22 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10596.076171875, "min": 9779.2509765625, "max": 29443.55859375, "count": 22 }, "SnowballTarget.Step.mean": { "value": 219992.0, "min": 9952.0, "max": 219992.0, "count": 22 }, "SnowballTarget.Step.sum": { "value": 219992.0, "min": 9952.0, "max": 219992.0, "count": 22 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.157833099365234, "min": 0.45086419582366943, "max": 12.157833099365234, "count": 22 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2480.197998046875, "min": 87.4676513671875, "max": 2480.197998046875, "count": 22 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 22 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 22 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06965578150457255, "min": 0.05857227130571332, "max": 0.07422991613751875, "count": 22 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3482789075228627, "min": 0.2616743308380155, "max": 0.3512510006380491, "count": 22 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19005702956050047, "min": 0.12550333928540533, "max": 0.2836234310678407, "count": 22 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9502851478025024, "min": 0.5020133571416213, "max": 1.4181171553392036, "count": 22 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.120097959999993e-06, "min": 6.120097959999993e-06, "max": 0.00029262000246, "count": 22 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.060048979999996e-05, "min": 3.060048979999996e-05, "max": 0.0013956000348, "count": 22 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10203999999999999, "min": 0.10203999999999999, "max": 0.19754000000000002, "count": 22 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5102, "min": 0.44616, "max": 0.9652000000000002, "count": 22 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00011179599999999988, "min": 0.00011179599999999988, "max": 0.004877246, "count": 22 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005589799999999994, "min": 0.0005589799999999994, "max": 0.023263480000000003, "count": 22 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.90740740740741, "min": 3.522727272727273, "max": 23.90740740740741, "count": 22 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1291.0, "min": 155.0, "max": 1306.0, "count": 22 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.90740740740741, "min": 3.522727272727273, "max": 23.90740740740741, "count": 22 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1291.0, "min": 155.0, "max": 1306.0, "count": 22 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 22 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680251070", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680251596" }, "total": 526.217956899, "count": 1, "self": 0.4328350230000524, "children": { "run_training.setup": { "total": 0.10668283199993311, "count": 1, "self": 0.10668283199993311 }, "TrainerController.start_learning": { "total": 525.678439044, "count": 1, "self": 0.6686095250202015, "children": { "TrainerController._reset_env": { "total": 3.815780942999936, "count": 1, "self": 3.815780942999936 }, "TrainerController.advance": { "total": 521.0643722089801, "count": 20078, "self": 0.3087317190054364, "children": { "env_step": { "total": 520.7556404899747, "count": 20078, "self": 380.98278943394484, "children": { "SubprocessEnvManager._take_step": { "total": 139.45396463198676, "count": 20078, "self": 2.0112132909926004, "children": { "TorchPolicy.evaluate": { "total": 137.44275134099416, "count": 20078, "self": 137.44275134099416 } } }, "workers": { "total": 0.31888642404305756, "count": 20078, "self": 0.0, "children": { "worker_root": { "total": 524.0173960119766, "count": 20078, "is_parallel": true, "self": 241.7524279499478, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0054838219998600835, "count": 1, "is_parallel": true, "self": 0.003928708000103143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015551139997569408, "count": 10, "is_parallel": true, "self": 0.0015551139997569408 } } }, "UnityEnvironment.step": { "total": 0.05364512999994986, "count": 1, "is_parallel": true, "self": 0.0006299010001384886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010993900000357826, "count": 1, "is_parallel": true, "self": 0.0010993900000357826 }, "communicator.exchange": { "total": 0.05002382299994679, "count": 1, "is_parallel": true, "self": 0.05002382299994679 }, "steps_from_proto": { "total": 0.0018920159998288, "count": 1, "is_parallel": true, "self": 0.0003920489996289689, "children": { "_process_rank_one_or_two_observation": { "total": 0.001499967000199831, "count": 10, "is_parallel": true, "self": 0.001499967000199831 } } } } } } }, "UnityEnvironment.step": { "total": 282.26496806202886, "count": 20077, "is_parallel": true, "self": 11.165753185946414, "children": { "UnityEnvironment._generate_step_input": { "total": 6.429724858024429, "count": 20077, "is_parallel": true, "self": 6.429724858024429 }, "communicator.exchange": { "total": 227.72859026403103, "count": 20077, "is_parallel": true, "self": 227.72859026403103 }, "steps_from_proto": { "total": 36.94089975402699, "count": 20077, "is_parallel": true, "self": 7.508476882952436, "children": { "_process_rank_one_or_two_observation": { "total": 29.43242287107455, "count": 200770, "is_parallel": true, "self": 29.43242287107455 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00037947700002405327, "count": 1, "self": 0.00037947700002405327, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 517.1657587470763, "count": 466170, "is_parallel": true, "self": 11.511085281968917, "children": { "process_trajectory": { "total": 286.6370546651078, "count": 466170, "is_parallel": true, "self": 283.1785471871085, "children": { "RLTrainer._checkpoint": { "total": 3.4585074779993192, "count": 11, "is_parallel": true, "self": 3.4585074779993192 } } }, "_update_policy": { "total": 219.01761879999958, "count": 100, "is_parallel": true, "self": 81.01951349499427, "children": { "TorchPPOOptimizer.update": { "total": 137.9981053050053, "count": 5097, "is_parallel": true, "self": 137.9981053050053 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12929688999975042, "count": 1, "self": 0.0010133709997717233, "children": { "RLTrainer._checkpoint": { "total": 0.1282835189999787, "count": 1, "self": 0.1282835189999787 } } } } } } }