{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7241389155387878, "min": 0.7241389155387878, "max": 2.8431262969970703, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7439.80322265625, "min": 7197.08984375, "max": 29116.45703125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.523112297058105, "min": 0.36638545989990234, "max": 13.523112297058105, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2758.71484375, "min": 71.07878112792969, "max": 2758.71484375, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07450274314831797, "min": 0.06197669490528129, "max": 0.0770327940759564, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3725137157415898, "min": 0.25445444828644626, "max": 0.3725137157415898, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1771096241240408, "min": 0.14638427946963073, "max": 0.3048295006886417, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8855481206202039, "min": 0.5855371178785229, "max": 1.4911954493499269, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.813431570666662e-06, "min": 8.813431570666662e-06, "max": 0.000490980001804, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.4067157853333307e-05, "min": 4.4067157853333307e-05, "max": 0.0023724000255199995, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.78181818181818, "min": 3.772727272727273, "max": 26.78181818181818, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1473.0, "min": 166.0, "max": 1473.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.78181818181818, "min": 3.772727272727273, "max": 26.78181818181818, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1473.0, "min": 166.0, "max": 1473.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1674323782", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1674324399" }, "total": 617.4343062629998, "count": 1, "self": 0.4324183260000609, "children": { "run_training.setup": { "total": 0.10077525199994852, "count": 1, "self": 0.10077525199994852 }, "TrainerController.start_learning": { "total": 616.9011126849998, "count": 1, "self": 0.9260756960200069, "children": { "TrainerController._reset_env": { "total": 9.381734026000004, "count": 1, "self": 9.381734026000004 }, "TrainerController.advance": { "total": 606.4768055889799, "count": 27336, "self": 0.4126399280048645, "children": { "env_step": { "total": 606.064165660975, "count": 27336, "self": 397.94491771393564, "children": { "SubprocessEnvManager._take_step": { "total": 207.73119733502017, "count": 27336, "self": 2.0244007900305405, "children": { "TorchPolicy.evaluate": { "total": 205.70679654498963, "count": 27336, "self": 44.75854074599488, "children": { "TorchPolicy.sample_actions": { "total": 160.94825579899475, "count": 27336, "self": 160.94825579899475 } } } } }, "workers": { "total": 0.3880506120192422, "count": 27336, "self": 0.0, "children": { "worker_root": { "total": 614.9494659030154, "count": 27336, "is_parallel": true, "self": 293.2734644780446, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008723600999928749, "count": 1, "is_parallel": true, "self": 0.0032962260004296695, "children": { "_process_rank_one_or_two_observation": { "total": 0.005427374999499079, "count": 10, "is_parallel": true, "self": 0.005427374999499079 } } }, "UnityEnvironment.step": { "total": 0.03266919199995755, "count": 1, "is_parallel": true, "self": 0.000630617000069833, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026718599997366255, "count": 1, "is_parallel": true, "self": 0.00026718599997366255 }, "communicator.exchange": { "total": 0.029939533000060692, "count": 1, "is_parallel": true, "self": 0.029939533000060692 }, "steps_from_proto": { "total": 0.0018318559998533601, "count": 1, "is_parallel": true, "self": 0.000418928999806667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014129270000466931, "count": 10, "is_parallel": true, "self": 0.0014129270000466931 } } } } } } }, "UnityEnvironment.step": { "total": 321.67600142497076, "count": 27335, "is_parallel": true, "self": 12.126362831022561, "children": { "UnityEnvironment._generate_step_input": { "total": 7.031739328991307, "count": 27335, "is_parallel": true, "self": 7.031739328991307 }, "communicator.exchange": { "total": 259.57100107797714, "count": 27335, "is_parallel": true, "self": 259.57100107797714 }, "steps_from_proto": { "total": 42.94689818697975, "count": 27335, "is_parallel": true, "self": 9.241207029007455, "children": { "_process_rank_one_or_two_observation": { "total": 33.705691157972296, "count": 273350, "is_parallel": true, "self": 33.705691157972296 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.153500003667432e-05, "count": 1, "self": 4.153500003667432e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 602.4849213489069, "count": 510583, "is_parallel": true, "self": 13.21204157298257, "children": { "process_trajectory": { "total": 344.28074944092464, "count": 510583, "is_parallel": true, "self": 343.15445014792454, "children": { "RLTrainer._checkpoint": { "total": 1.126299293000102, "count": 6, "is_parallel": true, "self": 1.126299293000102 } } }, "_update_policy": { "total": 244.99213033499973, "count": 136, "is_parallel": true, "self": 63.06705247799141, "children": { "TorchPPOOptimizer.update": { "total": 181.92507785700832, "count": 6933, "is_parallel": true, "self": 181.92507785700832 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11645583899985468, "count": 1, "self": 0.000898956999890288, "children": { "RLTrainer._checkpoint": { "total": 0.11555688199996439, "count": 1, "self": 0.11555688199996439 } } } } } } }