{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.920089602470398, "min": 0.920089602470398, "max": 2.8653457164764404, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8785.015625, "min": 8785.015625, "max": 29344.005859375, "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": 12.364646911621094, "min": 0.43879613280296326, "max": 12.364646911621094, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2411.106201171875, "min": 85.12644958496094, "max": 2507.57177734375, "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": 0.06601507702611807, "min": 0.06460780355658191, "max": 0.07495344347713112, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2640603081044723, "min": 0.25843121422632764, "max": 0.3747672173856556, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1972527807834102, "min": 0.11574097347728836, "max": 0.25219431922716257, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7890111231336407, "min": 0.46296389390915343, "max": 1.2609715961358128, "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": 24.136363636363637, "min": 3.409090909090909, "max": 24.545454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1062.0, "min": 150.0, "max": 1336.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.136363636363637, "min": 3.409090909090909, "max": 24.545454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1062.0, "min": 150.0, "max": 1336.0, "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": "1699819470", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699819930" }, "total": 459.63055783699997, "count": 1, "self": 0.4379853170000274, "children": { "run_training.setup": { "total": 0.044103188999997656, "count": 1, "self": 0.044103188999997656 }, "TrainerController.start_learning": { "total": 459.14846933099994, "count": 1, "self": 0.5199379810005098, "children": { "TrainerController._reset_env": { "total": 8.140162220000008, "count": 1, "self": 8.140162220000008 }, "TrainerController.advance": { "total": 450.4056870749995, "count": 18200, "self": 0.2436311609978361, "children": { "env_step": { "total": 450.16205591400166, "count": 18200, "self": 308.9103328580005, "children": { "SubprocessEnvManager._take_step": { "total": 140.9883870329968, "count": 18200, "self": 1.3737973169993154, "children": { "TorchPolicy.evaluate": { "total": 139.61458971599748, "count": 18200, "self": 139.61458971599748 } } }, "workers": { "total": 0.2633360230043422, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 457.9969619199971, "count": 18200, "is_parallel": true, "self": 223.00152597499263, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005004470999978139, "count": 1, "is_parallel": true, "self": 0.00365602499994111, "children": { "_process_rank_one_or_two_observation": { "total": 0.001348446000037029, "count": 10, "is_parallel": true, "self": 0.001348446000037029 } } }, "UnityEnvironment.step": { "total": 0.04347726599999646, "count": 1, "is_parallel": true, "self": 0.000661173999986886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004081940000162376, "count": 1, "is_parallel": true, "self": 0.0004081940000162376 }, "communicator.exchange": { "total": 0.04070699900000818, "count": 1, "is_parallel": true, "self": 0.04070699900000818 }, "steps_from_proto": { "total": 0.0017008989999851565, "count": 1, "is_parallel": true, "self": 0.0003026500000373744, "children": { "_process_rank_one_or_two_observation": { "total": 0.001398248999947782, "count": 10, "is_parallel": true, "self": 0.001398248999947782 } } } } } } }, "UnityEnvironment.step": { "total": 234.99543594500446, "count": 18199, "is_parallel": true, "self": 10.279258891001092, "children": { "UnityEnvironment._generate_step_input": { "total": 5.212588972001669, "count": 18199, "is_parallel": true, "self": 5.212588972001669 }, "communicator.exchange": { "total": 187.05113550199744, "count": 18199, "is_parallel": true, "self": 187.05113550199744 }, "steps_from_proto": { "total": 32.45245258000426, "count": 18199, "is_parallel": true, "self": 6.042761881993556, "children": { "_process_rank_one_or_two_observation": { "total": 26.409690698010706, "count": 181990, "is_parallel": true, "self": 26.409690698010706 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013815199997679883, "count": 1, "self": 0.00013815199997679883, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 446.7507119699794, "count": 467068, "is_parallel": true, "self": 9.794221145996516, "children": { "process_trajectory": { "total": 251.4024883419835, "count": 467068, "is_parallel": true, "self": 250.8991492099835, "children": { "RLTrainer._checkpoint": { "total": 0.5033391320000078, "count": 4, "is_parallel": true, "self": 0.5033391320000078 } } }, "_update_policy": { "total": 185.55400248199936, "count": 90, "is_parallel": true, "self": 57.72128485000172, "children": { "TorchPPOOptimizer.update": { "total": 127.83271763199764, "count": 4587, "is_parallel": true, "self": 127.83271763199764 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08254390299998704, "count": 1, "self": 0.0009472519999462747, "children": { "RLTrainer._checkpoint": { "total": 0.08159665100004077, "count": 1, "self": 0.08159665100004077 } } } } } } }