{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.49389326572418213, "min": 0.48974916338920593, "max": 0.8311858773231506, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4780.88671875, "min": 4665.3505859375, "max": 8503.03125, "count": 30 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 209936.0, "max": 499952.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.264318466186523, "min": 12.78330135345459, "max": 13.550152778625488, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2705.9208984375, "min": 2454.393798828125, "max": 2754.96923828125, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06444381270489162, "min": 0.06138828125846225, "max": 0.07410374682605798, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3222190635244581, "min": 0.245553125033849, "max": 0.35996163713257284, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16523896856050865, "min": 0.16523896856050865, "max": 0.20906220627766028, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8261948428025433, "min": 0.6695908378152287, "max": 1.0453110313883014, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.1056989647999945e-06, "min": 3.1056989647999945e-06, "max": 0.00017668564110480002, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5528494823999972e-05, "min": 1.5528494823999972e-05, "max": 0.000853728215424, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10103520000000002, "min": 0.10103520000000002, "max": 0.15889520000000001, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5051760000000001, "min": 0.4120608, "max": 0.7845760000000002, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.165647999999992e-05, "min": 6.165647999999992e-05, "max": 0.002948870480000001, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003082823999999996, "min": 0.0003082823999999996, "max": 0.0142503424, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.054545454545455, "min": 25.01818181818182, "max": 27.045454545454547, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1433.0, "min": 1106.0, "max": 1460.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.054545454545455, "min": 25.01818181818182, "max": 27.045454545454547, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1433.0, "min": 1106.0, "max": 1460.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690890343", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "0.31.0.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": "1690891037" }, "total": 694.623827245, "count": 1, "self": 0.43983715800004575, "children": { "run_training.setup": { "total": 0.0312753050000083, "count": 1, "self": 0.0312753050000083 }, "TrainerController.start_learning": { "total": 694.152714782, "count": 1, "self": 0.7819660919807347, "children": { "TrainerController._reset_env": { "total": 3.913775874999942, "count": 1, "self": 3.913775874999942 }, "TrainerController.advance": { "total": 689.3154025650192, "count": 27279, "self": 0.37225476100275046, "children": { "env_step": { "total": 688.9431478040165, "count": 27279, "self": 502.8756942400214, "children": { "SubprocessEnvManager._take_step": { "total": 185.61299342100756, "count": 27279, "self": 2.58825859700994, "children": { "TorchPolicy.evaluate": { "total": 183.02473482399762, "count": 27279, "self": 183.02473482399762 } } }, "workers": { "total": 0.45446014298750015, "count": 27279, "self": 0.0, "children": { "worker_root": { "total": 691.9716259699957, "count": 27279, "is_parallel": true, "self": 327.18913087799194, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018565589999752774, "count": 1, "is_parallel": true, "self": 0.000559727999984716, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012968309999905614, "count": 10, "is_parallel": true, "self": 0.0012968309999905614 } } }, "UnityEnvironment.step": { "total": 0.03499106699996446, "count": 1, "is_parallel": true, "self": 0.0006187319999071406, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004812870000705516, "count": 1, "is_parallel": true, "self": 0.0004812870000705516 }, "communicator.exchange": { "total": 0.0318589549999615, "count": 1, "is_parallel": true, "self": 0.0318589549999615 }, "steps_from_proto": { "total": 0.00203209300002527, "count": 1, "is_parallel": true, "self": 0.00048141700005999155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015506759999652786, "count": 10, "is_parallel": true, "self": 0.0015506759999652786 } } } } } } }, "UnityEnvironment.step": { "total": 364.7824950920037, "count": 27278, "is_parallel": true, "self": 15.603054116971748, "children": { "UnityEnvironment._generate_step_input": { "total": 7.835772952041566, "count": 27278, "is_parallel": true, "self": 7.835772952041566 }, "communicator.exchange": { "total": 290.0039097430006, "count": 27278, "is_parallel": true, "self": 290.0039097430006 }, "steps_from_proto": { "total": 51.33975827998984, "count": 27278, "is_parallel": true, "self": 9.260755715980281, "children": { "_process_rank_one_or_two_observation": { "total": 42.079002564009556, "count": 272780, "is_parallel": true, "self": 42.079002564009556 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010633400006554439, "count": 1, "self": 0.00010633400006554439, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 684.0919438569363, "count": 623524, "is_parallel": true, "self": 13.70914407186956, "children": { "process_trajectory": { "total": 367.81647221106573, "count": 623524, "is_parallel": true, "self": 366.1795820880658, "children": { "RLTrainer._checkpoint": { "total": 1.6368901229999437, "count": 6, "is_parallel": true, "self": 1.6368901229999437 } } }, "_update_policy": { "total": 302.566327574001, "count": 136, "is_parallel": true, "self": 122.20453180500476, "children": { "TorchPPOOptimizer.update": { "total": 180.36179576899622, "count": 6930, "is_parallel": true, "self": 180.36179576899622 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14146391600002062, "count": 1, "self": 0.0010155050001685595, "children": { "RLTrainer._checkpoint": { "total": 0.14044841099985206, "count": 1, "self": 0.14044841099985206 } } } } } } }