{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9425978064537048, "min": 0.9425978064537048, "max": 2.8655731678009033, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8999.923828125, "min": 8999.923828125, "max": 29346.3359375, "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": 12.625916481018066, "min": 0.26549282670021057, "max": 12.625916481018066, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2462.0537109375, "min": 51.50560760498047, "max": 2528.6044921875, "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": 0.07069972291883816, "min": 0.06450692044774199, "max": 0.07887540302951546, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28279889167535266, "min": 0.25802768179096797, "max": 0.3735034491144367, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22355725835351384, "min": 0.12405399122394109, "max": 0.28148188012487746, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8942290334140554, "min": 0.49621596489576436, "max": 1.4074094006243874, "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": 25.295454545454547, "min": 3.659090909090909, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1113.0, "min": 161.0, "max": 1368.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.295454545454547, "min": 3.659090909090909, "max": 25.295454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1113.0, "min": 161.0, "max": 1368.0, "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": "1673375893", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673376350" }, "total": 456.49883266999996, "count": 1, "self": 0.4347585950000621, "children": { "run_training.setup": { "total": 0.12241195899991908, "count": 1, "self": 0.12241195899991908 }, "TrainerController.start_learning": { "total": 455.941662116, "count": 1, "self": 0.6200736110051821, "children": { "TrainerController._reset_env": { "total": 8.118397348999906, "count": 1, "self": 8.118397348999906 }, "TrainerController.advance": { "total": 447.0692322189949, "count": 18201, "self": 0.29854688500597604, "children": { "env_step": { "total": 446.7706853339889, "count": 18201, "self": 293.8508929129831, "children": { "SubprocessEnvManager._take_step": { "total": 152.60731837200046, "count": 18201, "self": 1.4541804379991845, "children": { "TorchPolicy.evaluate": { "total": 151.15313793400128, "count": 18201, "self": 35.263469597008566, "children": { "TorchPolicy.sample_actions": { "total": 115.88966833699271, "count": 18201, "self": 115.88966833699271 } } } } }, "workers": { "total": 0.3124740490053455, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 454.4682973159928, "count": 18201, "is_parallel": true, "self": 217.74727682299874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005462211999997635, "count": 1, "is_parallel": true, "self": 0.0032804029999624618, "children": { "_process_rank_one_or_two_observation": { "total": 0.002181809000035173, "count": 10, "is_parallel": true, "self": 0.002181809000035173 } } }, "UnityEnvironment.step": { "total": 0.03473434800002906, "count": 1, "is_parallel": true, "self": 0.00042167399999470945, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038014799997654336, "count": 1, "is_parallel": true, "self": 0.00038014799997654336 }, "communicator.exchange": { "total": 0.0319902879999745, "count": 1, "is_parallel": true, "self": 0.0319902879999745 }, "steps_from_proto": { "total": 0.0019422380000833073, "count": 1, "is_parallel": true, "self": 0.0004421570000658903, "children": { "_process_rank_one_or_two_observation": { "total": 0.001500081000017417, "count": 10, "is_parallel": true, "self": 0.001500081000017417 } } } } } } }, "UnityEnvironment.step": { "total": 236.72102049299406, "count": 18200, "is_parallel": true, "self": 8.94533951298581, "children": { "UnityEnvironment._generate_step_input": { "total": 5.254987048999624, "count": 18200, "is_parallel": true, "self": 5.254987048999624 }, "communicator.exchange": { "total": 190.45197907200316, "count": 18200, "is_parallel": true, "self": 190.45197907200316 }, "steps_from_proto": { "total": 32.06871485900547, "count": 18200, "is_parallel": true, "self": 7.164690737993055, "children": { "_process_rank_one_or_two_observation": { "total": 24.904024121012412, "count": 182000, "is_parallel": true, "self": 24.904024121012412 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.8891000005824026e-05, "count": 1, "self": 4.8891000005824026e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.9031727410296, "count": 368553, "is_parallel": true, "self": 9.995390870989127, "children": { "process_trajectory": { "total": 253.36289070504074, "count": 368553, "is_parallel": true, "self": 252.58564174704054, "children": { "RLTrainer._checkpoint": { "total": 0.7772489580002002, "count": 4, "is_parallel": true, "self": 0.7772489580002002 } } }, "_update_policy": { "total": 180.54489116499974, "count": 90, "is_parallel": true, "self": 47.431419330989684, "children": { "TorchPPOOptimizer.update": { "total": 133.11347183401006, "count": 4587, "is_parallel": true, "self": 133.11347183401006 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13391004599998269, "count": 1, "self": 0.0008705719999397843, "children": { "RLTrainer._checkpoint": { "total": 0.1330394740000429, "count": 1, "self": 0.1330394740000429 } } } } } } }