{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6492751240730286, "min": 0.639085590839386, "max": 2.8672173023223877, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6777.783203125, "min": 5842.54833984375, "max": 30187.7109375, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.000293731689453, "min": 0.38188663125038147, "max": 14.130392074584961, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1372.02880859375, "min": 37.04300308227539, "max": 1452.5592041015625, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.622222222222224, "min": 4.181818181818182, "max": 28.056603773584907, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1243.0, "min": 184.0, "max": 1519.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.622222222222224, "min": 4.181818181818182, "max": 28.056603773584907, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1243.0, "min": 184.0, "max": 1519.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07168554315562063, "min": 0.057626276806352995, "max": 0.07645664880728159, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3584277157781032, "min": 0.24457293433906493, "max": 0.3796602218496321, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16574451748062582, "min": 0.14885324336150113, "max": 0.2811732024100481, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8287225874031291, "min": 0.5979540234102922, "max": 1.3142170038293388, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6800994400000014e-06, "min": 1.6800994400000014e-06, "max": 0.00029835000055, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.400497200000007e-06, "min": 8.400497200000007e-06, "max": 0.0014769000076999999, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10056000000000001, "min": 0.10056000000000001, "max": 0.19945000000000002, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5028, "min": 0.4062, "max": 0.9923000000000001, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.794400000000003e-05, "min": 3.794400000000003e-05, "max": 0.004972555, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00018972000000000016, "min": 0.00018972000000000016, "max": 0.02461577, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679060543", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679062698" }, "total": 2154.427509091, "count": 1, "self": 0.43582418300002246, "children": { "run_training.setup": { "total": 0.10953125100002126, "count": 1, "self": 0.10953125100002126 }, "TrainerController.start_learning": { "total": 2153.882153657, "count": 1, "self": 2.663554253995244, "children": { "TrainerController._reset_env": { "total": 10.10316233399999, "count": 1, "self": 10.10316233399999 }, "TrainerController.advance": { "total": 2140.9845051500047, "count": 90961, "self": 1.4327553439984513, "children": { "env_step": { "total": 2139.5517498060062, "count": 90961, "self": 1448.2912170569593, "children": { "SubprocessEnvManager._take_step": { "total": 689.8963431490463, "count": 90961, "self": 8.506576169990012, "children": { "TorchPolicy.evaluate": { "total": 681.3897669790563, "count": 90961, "self": 681.3897669790563 } } }, "workers": { "total": 1.3641896000004863, "count": 90961, "self": 0.0, "children": { "worker_root": { "total": 2146.8920126540006, "count": 90961, "is_parallel": true, "self": 965.3117495930464, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005134899000040605, "count": 1, "is_parallel": true, "self": 0.003570556000056513, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015643429999840919, "count": 10, "is_parallel": true, "self": 0.0015643429999840919 } } }, "UnityEnvironment.step": { "total": 0.034380645999988246, "count": 1, "is_parallel": true, "self": 0.0004157239999358353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030326300003480355, "count": 1, "is_parallel": true, "self": 0.00030326300003480355 }, "communicator.exchange": { "total": 0.03186396500001365, "count": 1, "is_parallel": true, "self": 0.03186396500001365 }, "steps_from_proto": { "total": 0.0017976940000039576, "count": 1, "is_parallel": true, "self": 0.0004624649999414032, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013352290000625544, "count": 10, "is_parallel": true, "self": 0.0013352290000625544 } } } } } } }, "UnityEnvironment.step": { "total": 1181.5802630609542, "count": 90960, "is_parallel": true, "self": 46.95053176501074, "children": { "UnityEnvironment._generate_step_input": { "total": 24.877781440958245, "count": 90960, "is_parallel": true, "self": 24.877781440958245 }, "communicator.exchange": { "total": 958.8299574970185, "count": 90960, "is_parallel": true, "self": 958.8299574970185 }, "steps_from_proto": { "total": 150.9219923579667, "count": 90960, "is_parallel": true, "self": 29.776023969981054, "children": { "_process_rank_one_or_two_observation": { "total": 121.14596838798565, "count": 909600, "is_parallel": true, "self": 121.14596838798565 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002587049998510338, "count": 1, "self": 0.0002587049998510338, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 2132.6253139590194, "count": 1107369, "is_parallel": true, "self": 27.86411536821288, "children": { "process_trajectory": { "total": 765.5610001138098, "count": 1107369, "is_parallel": true, "self": 760.9359834668091, "children": { "RLTrainer._checkpoint": { "total": 4.625016647000564, "count": 20, "is_parallel": true, "self": 4.625016647000564 } } }, "_update_policy": { "total": 1339.2001984769968, "count": 454, "is_parallel": true, "self": 392.11519133801835, "children": { "TorchPPOOptimizer.update": { "total": 947.0850071389784, "count": 23154, "is_parallel": true, "self": 947.0850071389784 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13067321400012588, "count": 1, "self": 0.0012712019997707102, "children": { "RLTrainer._checkpoint": { "total": 0.12940201200035517, "count": 1, "self": 0.12940201200035517 } } } } } } }