{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9817386269569397, "min": 0.977093517780304, "max": 2.861840009689331, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9384.439453125, "min": 9384.439453125, "max": 29434.025390625, "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": 13.030566215515137, "min": 0.2189708799123764, "max": 13.030566215515137, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2540.96044921875, "min": 42.480350494384766, "max": 2648.2783203125, "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": 0.06797949747609286, "min": 0.06127801654442652, "max": 0.07732554486816905, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27191798990437144, "min": 0.2451120661777061, "max": 0.36410143162927355, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18336444895933657, "min": 0.11654917633745307, "max": 0.27605305327212115, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7334577958373463, "min": 0.4661967053498123, "max": 1.3598530689875286, "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": 25.613636363636363, "min": 3.4318181818181817, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1127.0, "min": 151.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.613636363636363, "min": 3.4318181818181817, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1127.0, "min": 151.0, "max": 1415.0, "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": "1678819201", "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": "1678819693" }, "total": 491.9993122530001, "count": 1, "self": 0.43716862199994466, "children": { "run_training.setup": { "total": 0.10389752700007193, "count": 1, "self": 0.10389752700007193 }, "TrainerController.start_learning": { "total": 491.45824610400007, "count": 1, "self": 0.5810502609873538, "children": { "TrainerController._reset_env": { "total": 9.595026040999983, "count": 1, "self": 9.595026040999983 }, "TrainerController.advance": { "total": 481.14227002301277, "count": 18202, "self": 0.2897423299983757, "children": { "env_step": { "total": 480.8525276930144, "count": 18202, "self": 345.8918836910425, "children": { "SubprocessEnvManager._take_step": { "total": 134.6691143609944, "count": 18202, "self": 2.1572916649712397, "children": { "TorchPolicy.evaluate": { "total": 132.51182269602316, "count": 18202, "self": 132.51182269602316 } } }, "workers": { "total": 0.291529640977501, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 489.78323490200523, "count": 18202, "is_parallel": true, "self": 234.30261826099434, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005496287000028133, "count": 1, "is_parallel": true, "self": 0.003945667999914804, "children": { "_process_rank_one_or_two_observation": { "total": 0.001550619000113329, "count": 10, "is_parallel": true, "self": 0.001550619000113329 } } }, "UnityEnvironment.step": { "total": 0.0397360800000115, "count": 1, "is_parallel": true, "self": 0.0005931030000283499, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043236900000920286, "count": 1, "is_parallel": true, "self": 0.00043236900000920286 }, "communicator.exchange": { "total": 0.036656670000070335, "count": 1, "is_parallel": true, "self": 0.036656670000070335 }, "steps_from_proto": { "total": 0.00205393799990361, "count": 1, "is_parallel": true, "self": 0.0004184369998938564, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016355010000097536, "count": 10, "is_parallel": true, "self": 0.0016355010000097536 } } } } } } }, "UnityEnvironment.step": { "total": 255.4806166410109, "count": 18201, "is_parallel": true, "self": 9.927791786012904, "children": { "UnityEnvironment._generate_step_input": { "total": 5.6983893089822, "count": 18201, "is_parallel": true, "self": 5.6983893089822 }, "communicator.exchange": { "total": 206.15388432199381, "count": 18201, "is_parallel": true, "self": 206.15388432199381 }, "steps_from_proto": { "total": 33.70055122402198, "count": 18201, "is_parallel": true, "self": 6.809168889049374, "children": { "_process_rank_one_or_two_observation": { "total": 26.891382334972604, "count": 182010, "is_parallel": true, "self": 26.891382334972604 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017124100008913956, "count": 1, "self": 0.00017124100008913956, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 477.326186534979, "count": 437711, "is_parallel": true, "self": 11.1530747251104, "children": { "process_trajectory": { "total": 268.26712135486923, "count": 437711, "is_parallel": true, "self": 267.0619297788696, "children": { "RLTrainer._checkpoint": { "total": 1.2051915759996064, "count": 4, "is_parallel": true, "self": 1.2051915759996064 } } }, "_update_policy": { "total": 197.90599045499937, "count": 90, "is_parallel": true, "self": 71.28301668599511, "children": { "TorchPPOOptimizer.update": { "total": 126.62297376900426, "count": 4587, "is_parallel": true, "self": 126.62297376900426 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13972853799987206, "count": 1, "self": 0.0011796149999554473, "children": { "RLTrainer._checkpoint": { "total": 0.1385489229999166, "count": 1, "self": 0.1385489229999166 } } } } } } }