{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.757695198059082, "min": 2.757695198059082, "max": 2.8903231620788574, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 1941.41748046875, "min": 1920.7379150390625, "max": 4247.5859375, "count": 19 }, "SnowballTarget.Step.mean": { "value": 19968.0, "min": 1984.0, "max": 19968.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 19968.0, "min": 1984.0, "max": 19968.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.5668878555297852, "min": -0.12880820035934448, "max": 1.5668878555297852, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 26.63709259033203, "min": -1.932123064994812, "max": 35.6065673828125, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06757104229729842, "min": 0.06192646115703289, "max": 0.07440794752862227, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06757104229729842, "min": 0.06192646115703289, "max": 0.07440794752862227, "count": 8 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1923935004309112, "min": 0.12122674697699647, "max": 0.19640963363881206, "count": 8 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.1923935004309112, "min": 0.12122674697699647, "max": 0.19640963363881206, "count": 8 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6200094600000014e-05, "min": 1.6200094600000014e-05, "max": 0.0002472000176, "count": 8 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.6200094600000014e-05, "min": 1.6200094600000014e-05, "max": 0.0002472000176, "count": 8 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10540000000000004, "min": 0.10540000000000004, "max": 0.1824, "count": 8 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10540000000000004, "min": 0.10540000000000004, "max": 0.1824, "count": 8 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002794600000000003, "min": 0.0002794600000000003, "max": 0.004121760000000001, "count": 8 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002794600000000003, "min": 0.0002794600000000003, "max": 0.004121760000000001, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 7.5, "min": 3.272727272727273, "max": 7.5, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 15.0, "min": 9.0, "max": 57.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 7.5, "min": 3.272727272727273, "max": 7.5, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 15.0, "min": 9.0, "max": 57.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677758221", "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 --resume", "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": "1.22.4", "end_time_seconds": "1677758274" }, "total": 52.11257944100004, "count": 1, "self": 0.38679313200009346, "children": { "run_training.setup": { "total": 0.1765875169999731, "count": 1, "self": 0.1765875169999731 }, "TrainerController.start_learning": { "total": 51.54919879199997, "count": 1, "self": 0.09614634300106673, "children": { "TrainerController._reset_env": { "total": 6.931474111999989, "count": 1, "self": 6.931474111999989 }, "TrainerController.advance": { "total": 44.39882654399895, "count": 1736, "self": 0.02978044599859686, "children": { "env_step": { "total": 44.369046098000354, "count": 1736, "self": 31.12291286999971, "children": { "SubprocessEnvManager._take_step": { "total": 13.219065529999966, "count": 1736, "self": 0.1505733000006444, "children": { "TorchPolicy.evaluate": { "total": 13.068492229999322, "count": 1736, "self": 3.054521993000492, "children": { "TorchPolicy.sample_actions": { "total": 10.01397023699883, "count": 1736, "self": 10.01397023699883 } } } } }, "workers": { "total": 0.02706769800067832, "count": 1736, "self": 0.0, "children": { "worker_root": { "total": 51.41840059699922, "count": 1736, "is_parallel": true, "self": 27.998996483000155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026531170000225757, "count": 1, "is_parallel": true, "self": 0.0008188410000116164, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018342760000109593, "count": 10, "is_parallel": true, "self": 0.0018342760000109593 } } }, "UnityEnvironment.step": { "total": 0.041517863000024136, "count": 1, "is_parallel": true, "self": 0.00036195700005237086, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003225269999802549, "count": 1, "is_parallel": true, "self": 0.0003225269999802549 }, "communicator.exchange": { "total": 0.03908663599997908, "count": 1, "is_parallel": true, "self": 0.03908663599997908 }, "steps_from_proto": { "total": 0.0017467430000124295, "count": 1, "is_parallel": true, "self": 0.0004178030001185107, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013289399998939189, "count": 10, "is_parallel": true, "self": 0.0013289399998939189 } } } } } } }, "UnityEnvironment.step": { "total": 23.419404113999065, "count": 1735, "is_parallel": true, "self": 0.9261710039979789, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5086356000018668, "count": 1735, "is_parallel": true, "self": 0.5086356000018668 }, "communicator.exchange": { "total": 18.841391709999584, "count": 1735, "is_parallel": true, "self": 18.841391709999584 }, "steps_from_proto": { "total": 3.1432057999996346, "count": 1735, "is_parallel": true, "self": 0.6918250430020407, "children": { "_process_rank_one_or_two_observation": { "total": 2.451380756997594, "count": 17350, "is_parallel": true, "self": 2.451380756997594 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003116940000040813, "count": 1, "self": 0.0003116940000040813, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 44.13281091199889, "count": 38481, "is_parallel": true, "self": 0.9294721670049171, "children": { "process_trajectory": { "total": 26.786279621994026, "count": 38481, "is_parallel": true, "self": 25.433308435994093, "children": { "RLTrainer._checkpoint": { "total": 1.3529711859999338, "count": 4, "is_parallel": true, "self": 1.3529711859999338 } } }, "_update_policy": { "total": 16.417059122999945, "count": 8, "is_parallel": true, "self": 5.4154798449998225, "children": { "TorchPPOOptimizer.update": { "total": 11.001579278000122, "count": 405, "is_parallel": true, "self": 11.001579278000122 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12244009899995945, "count": 1, "self": 0.0011683529999118036, "children": { "RLTrainer._checkpoint": { "total": 0.12127174600004764, "count": 1, "self": 0.12127174600004764 } } } } } } }