{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8228198885917664, "min": 0.8228198885917664, "max": 2.8753726482391357, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7856.2841796875, "min": 7856.2841796875, "max": 29415.0625, "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": 12.91717529296875, "min": 0.3538360893726349, "max": 12.91717529296875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2518.84912109375, "min": 68.64420318603516, "max": 2633.417236328125, "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": 0.06910795258590952, "min": 0.0627614049339101, "max": 0.07488940514746241, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27643181034363806, "min": 0.2674349876275907, "max": 0.3697077095264331, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1921140032948232, "min": 0.09805602815650476, "max": 0.28989981190831055, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7684560131792928, "min": 0.39222411262601903, "max": 1.4494990595415527, "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": 25.318181818181817, "min": 2.9545454545454546, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1114.0, "min": 130.0, "max": 1422.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.318181818181817, "min": 2.9545454545454546, "max": 25.854545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1114.0, "min": 130.0, "max": 1422.0, "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": "1719507968", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719508481" }, "total": 513.093901985, "count": 1, "self": 0.495395513999938, "children": { "run_training.setup": { "total": 0.06100723600002311, "count": 1, "self": 0.06100723600002311 }, "TrainerController.start_learning": { "total": 512.537499235, "count": 1, "self": 0.6554796229956992, "children": { "TrainerController._reset_env": { "total": 3.002359573999911, "count": 1, "self": 3.002359573999911 }, "TrainerController.advance": { "total": 508.75587499600465, "count": 18203, "self": 0.30834997102010675, "children": { "env_step": { "total": 508.44752502498454, "count": 18203, "self": 335.6080047249909, "children": { "SubprocessEnvManager._take_step": { "total": 172.52004412200608, "count": 18203, "self": 1.69218564701805, "children": { "TorchPolicy.evaluate": { "total": 170.82785847498803, "count": 18203, "self": 170.82785847498803 } } }, "workers": { "total": 0.31947617798755346, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 511.0847046600097, "count": 18203, "is_parallel": true, "self": 254.50485618898438, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0057022040000447305, "count": 1, "is_parallel": true, "self": 0.003612027999906786, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020901760001379444, "count": 10, "is_parallel": true, "self": 0.0020901760001379444 } } }, "UnityEnvironment.step": { "total": 0.037385114999779034, "count": 1, "is_parallel": true, "self": 0.0007347499999923457, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043912999990425305, "count": 1, "is_parallel": true, "self": 0.00043912999990425305 }, "communicator.exchange": { "total": 0.03424748399993405, "count": 1, "is_parallel": true, "self": 0.03424748399993405 }, "steps_from_proto": { "total": 0.001963750999948388, "count": 1, "is_parallel": true, "self": 0.0004200529995159741, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015436980004324141, "count": 10, "is_parallel": true, "self": 0.0015436980004324141 } } } } } } }, "UnityEnvironment.step": { "total": 256.57984847102534, "count": 18202, "is_parallel": true, "self": 11.498756508020733, "children": { "UnityEnvironment._generate_step_input": { "total": 5.973715494998487, "count": 18202, "is_parallel": true, "self": 5.973715494998487 }, "communicator.exchange": { "total": 201.07022912600428, "count": 18202, "is_parallel": true, "self": 201.07022912600428 }, "steps_from_proto": { "total": 38.037147342001845, "count": 18202, "is_parallel": true, "self": 7.337061423009118, "children": { "_process_rank_one_or_two_observation": { "total": 30.700085918992727, "count": 182020, "is_parallel": true, "self": 30.700085918992727 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012145799996687856, "count": 1, "self": 0.00012145799996687856, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 502.44372465297965, "count": 729253, "is_parallel": true, "self": 16.047309458962445, "children": { "process_trajectory": { "total": 277.5377121910178, "count": 729253, "is_parallel": true, "self": 276.26115166301815, "children": { "RLTrainer._checkpoint": { "total": 1.2765605279996635, "count": 4, "is_parallel": true, "self": 1.2765605279996635 } } }, "_update_policy": { "total": 208.8587030029994, "count": 90, "is_parallel": true, "self": 67.31194280899149, "children": { "TorchPPOOptimizer.update": { "total": 141.5467601940079, "count": 4584, "is_parallel": true, "self": 141.5467601940079 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12366358399981436, "count": 1, "self": 0.0011488809998354554, "children": { "RLTrainer._checkpoint": { "total": 0.12251470299997891, "count": 1, "self": 0.12251470299997891 } } } } } } }