{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.044773817062378, "min": 1.0364598035812378, "max": 2.85550856590271, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9975.5, "min": 9975.5, "max": 29337.494140625, "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": 12.26220703125, "min": 0.38965272903442383, "max": 12.26220703125, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2391.13037109375, "min": 75.5926284790039, "max": 2455.4599609375, "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": 0.07113868604738302, "min": 0.06174491895602413, "max": 0.07599664517500274, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2845547441895321, "min": 0.24697967582409652, "max": 0.37998322587501365, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21096540585744616, "min": 0.11676170514079322, "max": 0.30364713350347444, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8438616234297847, "min": 0.46704682056317287, "max": 1.3884522041269378, "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": 24.272727272727273, "min": 3.340909090909091, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1068.0, "min": 147.0, "max": 1332.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.272727272727273, "min": 3.340909090909091, "max": 24.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1068.0, "min": 147.0, "max": 1332.0, "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": "1701029820", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701030305" }, "total": 484.75184117200024, "count": 1, "self": 0.5443034180002542, "children": { "run_training.setup": { "total": 0.05587426600004619, "count": 1, "self": 0.05587426600004619 }, "TrainerController.start_learning": { "total": 484.15166348799994, "count": 1, "self": 0.5900411750017156, "children": { "TrainerController._reset_env": { "total": 3.4015100229999007, "count": 1, "self": 3.4015100229999007 }, "TrainerController.advance": { "total": 480.06972950299814, "count": 18199, "self": 0.28258700097148903, "children": { "env_step": { "total": 479.78714250202665, "count": 18199, "self": 327.2707283880786, "children": { "SubprocessEnvManager._take_step": { "total": 152.23011439097627, "count": 18199, "self": 1.5124215190116956, "children": { "TorchPolicy.evaluate": { "total": 150.71769287196457, "count": 18199, "self": 150.71769287196457 } } }, "workers": { "total": 0.2862997229717621, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 482.8412272840087, "count": 18199, "is_parallel": true, "self": 235.89776919099404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004929642999741191, "count": 1, "is_parallel": true, "self": 0.003380601999197097, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015490410005440935, "count": 10, "is_parallel": true, "self": 0.0015490410005440935 } } }, "UnityEnvironment.step": { "total": 0.03440026299995225, "count": 1, "is_parallel": true, "self": 0.000615170999935799, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038080500007708906, "count": 1, "is_parallel": true, "self": 0.00038080500007708906 }, "communicator.exchange": { "total": 0.031488114000239875, "count": 1, "is_parallel": true, "self": 0.031488114000239875 }, "steps_from_proto": { "total": 0.0019161729996994836, "count": 1, "is_parallel": true, "self": 0.00036640999951487174, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015497630001846119, "count": 10, "is_parallel": true, "self": 0.0015497630001846119 } } } } } } }, "UnityEnvironment.step": { "total": 246.94345809301467, "count": 18198, "is_parallel": true, "self": 10.604548230074215, "children": { "UnityEnvironment._generate_step_input": { "total": 5.274229455986642, "count": 18198, "is_parallel": true, "self": 5.274229455986642 }, "communicator.exchange": { "total": 197.0497605530236, "count": 18198, "is_parallel": true, "self": 197.0497605530236 }, "steps_from_proto": { "total": 34.01491985393022, "count": 18198, "is_parallel": true, "self": 6.353052049070811, "children": { "_process_rank_one_or_two_observation": { "total": 27.661867804859412, "count": 181980, "is_parallel": true, "self": 27.661867804859412 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017616400009501376, "count": 1, "self": 0.00017616400009501376, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 475.8580951160493, "count": 510078, "is_parallel": true, "self": 11.266719519112485, "children": { "process_trajectory": { "total": 268.2964393949369, "count": 510078, "is_parallel": true, "self": 267.40330567293677, "children": { "RLTrainer._checkpoint": { "total": 0.8931337220001296, "count": 4, "is_parallel": true, "self": 0.8931337220001296 } } }, "_update_policy": { "total": 196.29493620199992, "count": 90, "is_parallel": true, "self": 67.0223303920402, "children": { "TorchPPOOptimizer.update": { "total": 129.2726058099597, "count": 4587, "is_parallel": true, "self": 129.2726058099597 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09020662300008553, "count": 1, "self": 0.000964174999808165, "children": { "RLTrainer._checkpoint": { "total": 0.08924244800027736, "count": 1, "self": 0.08924244800027736 } } } } } } }