{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0493799448013306, "min": 1.0464460849761963, "max": 2.8779244422912598, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9984.8505859375, "min": 9984.8505859375, "max": 29472.82421875, "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": 12.53875732421875, "min": 0.33331069350242615, "max": 12.53875732421875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2445.0576171875, "min": 64.66227722167969, "max": 2533.000244140625, "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": 0.0696226267067615, "min": 0.06297429086413353, "max": 0.07435977417109967, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.278490506827046, "min": 0.26063525885647143, "max": 0.36314051821953436, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21283175635571572, "min": 0.1095688995624454, "max": 0.2742007432468966, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8513270254228629, "min": 0.4382755982497816, "max": 1.370391531902201, "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": 24.727272727272727, "min": 3.1136363636363638, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 137.0, "max": 1374.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.1136363636363638, "max": 24.98181818181818, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 137.0, "max": 1374.0, "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": "1682324660", "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": "1682325140" }, "total": 480.41623877899997, "count": 1, "self": 0.6596349910000754, "children": { "run_training.setup": { "total": 0.12037732199996753, "count": 1, "self": 0.12037732199996753 }, "TrainerController.start_learning": { "total": 479.6362264659999, "count": 1, "self": 0.5995256139990488, "children": { "TrainerController._reset_env": { "total": 3.7945856009999943, "count": 1, "self": 3.7945856009999943 }, "TrainerController.advance": { "total": 475.0284430790009, "count": 18201, "self": 0.31098065799943697, "children": { "env_step": { "total": 474.71746242100147, "count": 18201, "self": 346.78862283599284, "children": { "SubprocessEnvManager._take_step": { "total": 127.63336788700309, "count": 18201, "self": 1.752895787006878, "children": { "TorchPolicy.evaluate": { "total": 125.88047209999621, "count": 18201, "self": 125.88047209999621 } } }, "workers": { "total": 0.2954716980055423, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 477.85601669999465, "count": 18201, "is_parallel": true, "self": 221.16729208699155, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007990067999969597, "count": 1, "is_parallel": true, "self": 0.00658312900003466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014069389999349369, "count": 10, "is_parallel": true, "self": 0.0014069389999349369 } } }, "UnityEnvironment.step": { "total": 0.04945860600003016, "count": 1, "is_parallel": true, "self": 0.0005599140000072111, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047632499996552724, "count": 1, "is_parallel": true, "self": 0.00047632499996552724 }, "communicator.exchange": { "total": 0.046426918000008754, "count": 1, "is_parallel": true, "self": 0.046426918000008754 }, "steps_from_proto": { "total": 0.0019954490000486658, "count": 1, "is_parallel": true, "self": 0.0004095150000011927, "children": { "_process_rank_one_or_two_observation": { "total": 0.001585934000047473, "count": 10, "is_parallel": true, "self": 0.001585934000047473 } } } } } } }, "UnityEnvironment.step": { "total": 256.6887246130031, "count": 18200, "is_parallel": true, "self": 10.190582948011127, "children": { "UnityEnvironment._generate_step_input": { "total": 5.766916357999264, "count": 18200, "is_parallel": true, "self": 5.766916357999264 }, "communicator.exchange": { "total": 206.5244268899985, "count": 18200, "is_parallel": true, "self": 206.5244268899985 }, "steps_from_proto": { "total": 34.20679841699422, "count": 18200, "is_parallel": true, "self": 6.828961884984608, "children": { "_process_rank_one_or_two_observation": { "total": 27.37783653200961, "count": 182000, "is_parallel": true, "self": 27.37783653200961 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.029000002807152e-05, "count": 1, "self": 8.029000002807152e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 471.3200813950316, "count": 433675, "is_parallel": true, "self": 10.74021796409221, "children": { "process_trajectory": { "total": 261.95091090993935, "count": 433675, "is_parallel": true, "self": 261.0361808349395, "children": { "RLTrainer._checkpoint": { "total": 0.9147300749998521, "count": 4, "is_parallel": true, "self": 0.9147300749998521 } } }, "_update_policy": { "total": 198.62895252100003, "count": 90, "is_parallel": true, "self": 72.38050130300616, "children": { "TorchPPOOptimizer.update": { "total": 126.24845121799387, "count": 4587, "is_parallel": true, "self": 126.24845121799387 } } } } } } } } }, "TrainerController._save_models": { "total": 0.21359188199994605, "count": 1, "self": 0.0011803710000322098, "children": { "RLTrainer._checkpoint": { "total": 0.21241151099991384, "count": 1, "self": 0.21241151099991384 } } } } } } }