{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0087414979934692, "min": 1.0087414979934692, "max": 2.8711769580841064, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9698.041015625, "min": 9698.041015625, "max": 29530.0546875, "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": 13.111385345458984, "min": 0.4244138300418854, "max": 13.111385345458984, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2556.72021484375, "min": 82.3362808227539, "max": 2622.6513671875, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.mean": { "value": 0.10785937309265137, "min": 0.0557728111743927, "max": 0.1300487220287323, "count": 20 }, "SnowballTarget.Policy.CuriosityValueEstimate.sum": { "value": 21.032577514648438, "min": 10.819925308227539, "max": 26.659988403320312, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06339533592936099, "min": 0.06339533592936099, "max": 0.07467216342509561, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25358134371744395, "min": 0.25358134371744395, "max": 0.37336081712547803, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.10095915037627314, "min": 0.058808436063711764, "max": 0.15426495539791443, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.40383660150509254, "min": 0.23523374425484705, "max": 0.760506571800101, "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.Losses.CuriosityForwardLoss.mean": { "value": 0.05046149637257936, "min": 0.05046149637257936, "max": 0.15533913419508905, "count": 20 }, "SnowballTarget.Losses.CuriosityForwardLoss.sum": { "value": 0.20184598549031743, "min": 0.20184598549031743, "max": 0.6213565367803562, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.mean": { "value": 0.8772795074710659, "min": 0.8772795074710659, "max": 2.7623275714177713, "count": 20 }, "SnowballTarget.Losses.CuriosityInverseLoss.sum": { "value": 3.5091180298842635, "min": 3.5091180298842635, "max": 13.007927244784785, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.931818181818183, "min": 3.4318181818181817, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1141.0, "min": 151.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.931818181818183, "min": 3.4318181818181817, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1141.0, "min": 151.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.mean": { "value": 0.2078767866689966, "min": 0.2078767866689966, "max": 0.3299151224041866, "count": 20 }, "SnowballTarget.Policy.CuriosityReward.sum": { "value": 9.14657861343585, "min": 9.14657861343585, "max": 17.822517244145274, "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": "1691073296", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1691073839" }, "total": 543.516846515, "count": 1, "self": 0.7961708080001699, "children": { "run_training.setup": { "total": 0.04400297699976363, "count": 1, "self": 0.04400297699976363 }, "TrainerController.start_learning": { "total": 542.6766727300001, "count": 1, "self": 0.5892676990188193, "children": { "TrainerController._reset_env": { "total": 5.335567161000199, "count": 1, "self": 5.335567161000199 }, "TrainerController.advance": { "total": 536.5361500499807, "count": 18214, "self": 0.2825607829654473, "children": { "env_step": { "total": 536.2535892670153, "count": 18214, "self": 413.36034684601464, "children": { "SubprocessEnvManager._take_step": { "total": 122.59732833197859, "count": 18214, "self": 1.73446747293292, "children": { "TorchPolicy.evaluate": { "total": 120.86286085904567, "count": 18214, "self": 120.86286085904567 } } }, "workers": { "total": 0.2959140890220624, "count": 18214, "self": 0.0, "children": { "worker_root": { "total": 540.9849294739902, "count": 18214, "is_parallel": true, "self": 290.4034028800156, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005830562000028294, "count": 1, "is_parallel": true, "self": 0.004201572000056331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016289899999719637, "count": 10, "is_parallel": true, "self": 0.0016289899999719637 } } }, "UnityEnvironment.step": { "total": 0.04226209899979949, "count": 1, "is_parallel": true, "self": 0.0006236359995455132, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042012200037788716, "count": 1, "is_parallel": true, "self": 0.00042012200037788716 }, "communicator.exchange": { "total": 0.039248030000180734, "count": 1, "is_parallel": true, "self": 0.039248030000180734 }, "steps_from_proto": { "total": 0.001970310999695357, "count": 1, "is_parallel": true, "self": 0.00040998499889610684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015603260007992503, "count": 10, "is_parallel": true, "self": 0.0015603260007992503 } } } } } } }, "UnityEnvironment.step": { "total": 250.58152659397456, "count": 18213, "is_parallel": true, "self": 10.764362944925324, "children": { "UnityEnvironment._generate_step_input": { "total": 5.532766402046946, "count": 18213, "is_parallel": true, "self": 5.532766402046946 }, "communicator.exchange": { "total": 197.4621343059939, "count": 18213, "is_parallel": true, "self": 197.4621343059939 }, "steps_from_proto": { "total": 36.822262941008375, "count": 18213, "is_parallel": true, "self": 6.679355254996153, "children": { "_process_rank_one_or_two_observation": { "total": 30.142907686012222, "count": 182130, "is_parallel": true, "self": 30.142907686012222 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015675300028306083, "count": 1, "self": 0.00015675300028306083, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 533.4009280909572, "count": 385175, "is_parallel": true, "self": 8.903886021814742, "children": { "process_trajectory": { "total": 270.40538875714583, "count": 385175, "is_parallel": true, "self": 267.7706257441455, "children": { "RLTrainer._checkpoint": { "total": 2.634763013000338, "count": 4, "is_parallel": true, "self": 2.634763013000338 } } }, "_update_policy": { "total": 254.09165331199665, "count": 90, "is_parallel": true, "self": 156.89597449300572, "children": { "TorchPPOOptimizer.update": { "total": 97.19567881899093, "count": 4584, "is_parallel": true, "self": 97.19567881899093 } } } } } } } } }, "TrainerController._save_models": { "total": 0.215531067000029, "count": 1, "self": 0.002977705000375863, "children": { "RLTrainer._checkpoint": { "total": 0.21255336199965313, "count": 1, "self": 0.21255336199965313 } } } } } } }