{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9632812738418579, "min": 0.9246783256530762, "max": 2.870723247528076, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9155.025390625, "min": 9155.025390625, "max": 29304.34375, "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": 11.64111042022705, "min": 0.36670923233032227, "max": 11.64111042022705, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2270.0166015625, "min": 71.14159393310547, "max": 2352.35693359375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06682522337445441, "min": 0.06518859257917653, "max": 0.07374642144012102, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26730089349781766, "min": 0.2607543703167061, "max": 0.36873210720060506, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18411600323138286, "min": 0.12943461725223518, "max": 0.28916128951252673, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7364640129255314, "min": 0.5177384690089407, "max": 1.284586973342241, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.3880973060000045e-06, "min": 5.3880973060000045e-06, "max": 0.00019458800270600002, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.1552389224000018e-05, "min": 2.1552389224000018e-05, "max": 0.0009234400382800001, "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.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.Environment.CumulativeReward.mean": { "value": 22.90909090909091, "min": 3.8181818181818183, "max": 22.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1008.0, "min": 168.0, "max": 1240.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.90909090909091, "min": 3.8181818181818183, "max": 22.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1008.0, "min": 168.0, "max": 1240.0, "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": "1743534259", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743534723" }, "total": 463.4148305289998, "count": 1, "self": 0.4934363839997786, "children": { "run_training.setup": { "total": 0.026054358000010325, "count": 1, "self": 0.026054358000010325 }, "TrainerController.start_learning": { "total": 462.895339787, "count": 1, "self": 0.4407009419858241, "children": { "TrainerController._reset_env": { "total": 3.337629280999863, "count": 1, "self": 3.337629280999863 }, "TrainerController.advance": { "total": 459.0257366540143, "count": 18192, "self": 0.4386295179847366, "children": { "env_step": { "total": 328.0134578470047, "count": 18192, "self": 251.3027630620104, "children": { "SubprocessEnvManager._take_step": { "total": 76.46558980901091, "count": 18192, "self": 1.433017349016609, "children": { "TorchPolicy.evaluate": { "total": 75.0325724599943, "count": 18192, "self": 75.0325724599943 } } }, "workers": { "total": 0.24510497598339498, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 461.22355163601037, "count": 18192, "is_parallel": true, "self": 241.5270835029835, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0061535980000826385, "count": 1, "is_parallel": true, "self": 0.004519372999084226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016342250009984127, "count": 10, "is_parallel": true, "self": 0.0016342250009984127 } } }, "UnityEnvironment.step": { "total": 0.03771729200002483, "count": 1, "is_parallel": true, "self": 0.0006177939999361115, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004078430001754896, "count": 1, "is_parallel": true, "self": 0.0004078430001754896 }, "communicator.exchange": { "total": 0.034667848000026424, "count": 1, "is_parallel": true, "self": 0.034667848000026424 }, "steps_from_proto": { "total": 0.0020238069998868013, "count": 1, "is_parallel": true, "self": 0.0003686319998905674, "children": { "_process_rank_one_or_two_observation": { "total": 0.001655174999996234, "count": 10, "is_parallel": true, "self": 0.001655174999996234 } } } } } } }, "UnityEnvironment.step": { "total": 219.69646813302688, "count": 18191, "is_parallel": true, "self": 10.213131535019556, "children": { "UnityEnvironment._generate_step_input": { "total": 5.647620873000733, "count": 18191, "is_parallel": true, "self": 5.647620873000733 }, "communicator.exchange": { "total": 171.01013484000237, "count": 18191, "is_parallel": true, "self": 171.01013484000237 }, "steps_from_proto": { "total": 32.82558088500423, "count": 18191, "is_parallel": true, "self": 6.1539134649615335, "children": { "_process_rank_one_or_two_observation": { "total": 26.671667420042695, "count": 181910, "is_parallel": true, "self": 26.671667420042695 } } } } } } } } } } }, "trainer_advance": { "total": 130.57364928902484, "count": 18192, "self": 0.5922123160366937, "children": { "process_trajectory": { "total": 28.589803069987283, "count": 18192, "self": 27.938397997987295, "children": { "RLTrainer._checkpoint": { "total": 0.6514050719999886, "count": 4, "self": 0.6514050719999886 } } }, "_update_policy": { "total": 101.39163390300087, "count": 90, "self": 40.31287505400269, "children": { "TorchPPOOptimizer.update": { "total": 61.07875884899818, "count": 4587, "self": 61.07875884899818 } } } } } } }, "trainer_threads": { "total": 9.010000212583691e-07, "count": 1, "self": 9.010000212583691e-07 }, "TrainerController._save_models": { "total": 0.09127200900002208, "count": 1, "self": 0.0008828480001739081, "children": { "RLTrainer._checkpoint": { "total": 0.09038916099984817, "count": 1, "self": 0.09038916099984817 } } } } } } }