{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2860615253448486, "min": 1.2419261932373047, "max": 2.8552134037017822, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12293.4619140625, "min": 12293.4619140625, "max": 29240.240234375, "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": 64.10287475585938, "min": 0.505084216594696, "max": 64.10287475585938, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 12500.060546875, "min": 97.98633575439453, "max": 12500.060546875, "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": 0.06621475017734565, "min": 0.06200313892891156, "max": 0.07302246726484395, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2648590007093826, "min": 0.25388889340170223, "max": 0.3490614113193884, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.8442495814433285, "min": 0.18865362484939396, "max": 0.8442495814433285, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 3.376998325773314, "min": 0.7546144993975759, "max": 3.8259938470288812, "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": 22.25, "min": 3.7954545454545454, "max": 22.25, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 979.0, "min": 167.0, "max": 1215.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.25, "min": 3.7954545454545454, "max": 22.25, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 979.0, "min": 167.0, "max": 1215.0, "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": "1689435683", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689436156" }, "total": 473.12772343000006, "count": 1, "self": 0.7914289590000294, "children": { "run_training.setup": { "total": 0.062190289999989545, "count": 1, "self": 0.062190289999989545 }, "TrainerController.start_learning": { "total": 472.27410418100004, "count": 1, "self": 0.5438083420038993, "children": { "TrainerController._reset_env": { "total": 4.9842468819999795, "count": 1, "self": 4.9842468819999795 }, "TrainerController.advance": { "total": 466.5209851369961, "count": 18213, "self": 0.28948835098293557, "children": { "env_step": { "total": 466.23149678601317, "count": 18213, "self": 340.9007732520104, "children": { "SubprocessEnvManager._take_step": { "total": 125.05958207200382, "count": 18213, "self": 1.8583368140090215, "children": { "TorchPolicy.evaluate": { "total": 123.2012452579948, "count": 18213, "self": 123.2012452579948 } } }, "workers": { "total": 0.27114146199892275, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 470.6075418089979, "count": 18213, "is_parallel": true, "self": 219.0485352079976, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006492166000043653, "count": 1, "is_parallel": true, "self": 0.004237468000098943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022546979999447103, "count": 10, "is_parallel": true, "self": 0.0022546979999447103 } } }, "UnityEnvironment.step": { "total": 0.04228143400001727, "count": 1, "is_parallel": true, "self": 0.00047545299997864277, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003390110000509594, "count": 1, "is_parallel": true, "self": 0.0003390110000509594 }, "communicator.exchange": { "total": 0.03978238299998793, "count": 1, "is_parallel": true, "self": 0.03978238299998793 }, "steps_from_proto": { "total": 0.0016845869999997376, "count": 1, "is_parallel": true, "self": 0.00034923200001912846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013353549999806091, "count": 10, "is_parallel": true, "self": 0.0013353549999806091 } } } } } } }, "UnityEnvironment.step": { "total": 251.5590066010003, "count": 18212, "is_parallel": true, "self": 10.772451217007642, "children": { "UnityEnvironment._generate_step_input": { "total": 5.313815581998654, "count": 18212, "is_parallel": true, "self": 5.313815581998654 }, "communicator.exchange": { "total": 199.52079520099505, "count": 18212, "is_parallel": true, "self": 199.52079520099505 }, "steps_from_proto": { "total": 35.95194460099896, "count": 18212, "is_parallel": true, "self": 6.4805869980046396, "children": { "_process_rank_one_or_two_observation": { "total": 29.471357602994317, "count": 182120, "is_parallel": true, "self": 29.471357602994317 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013210600002366846, "count": 1, "self": 0.00013210600002366846, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 463.12736518802564, "count": 437211, "is_parallel": true, "self": 9.38639839897985, "children": { "process_trajectory": { "total": 252.11443535504526, "count": 437211, "is_parallel": true, "self": 250.35231033304535, "children": { "RLTrainer._checkpoint": { "total": 1.762125021999907, "count": 4, "is_parallel": true, "self": 1.762125021999907 } } }, "_update_policy": { "total": 201.62653143400053, "count": 90, "is_parallel": true, "self": 77.4614314459987, "children": { "TorchPPOOptimizer.update": { "total": 124.16509998800183, "count": 4584, "is_parallel": true, "self": 124.16509998800183 } } } } } } } } }, "TrainerController._save_models": { "total": 0.22493171400003575, "count": 1, "self": 0.0011633039999878747, "children": { "RLTrainer._checkpoint": { "total": 0.22376841000004788, "count": 1, "self": 0.22376841000004788 } } } } } } }