{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.045287847518921, "min": 1.045287847518921, "max": 2.856492757797241, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10049.3974609375, "min": 10049.3974609375, "max": 29347.60546875, "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": 13.52973747253418, "min": 0.3814617693424225, "max": 13.53261947631836, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2638.298828125, "min": 74.00358581542969, "max": 2760.654296875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06734420754533038, "min": 0.06432966824521667, "max": 0.07639496337836973, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2693768301813215, "min": 0.2573186729808667, "max": 0.3722314807140113, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18734827232273185, "min": 0.11762163458236802, "max": 0.27707308786464674, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7493930892909274, "min": 0.47048653832947207, "max": 1.3770913145705768, "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": 26.272727272727273, "min": 3.4545454545454546, "max": 26.618181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1156.0, "min": 152.0, "max": 1464.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 3.4545454545454546, "max": 26.618181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1156.0, "min": 152.0, "max": 1464.0, "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": "1678292423", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678292911" }, "total": 487.837692687, "count": 1, "self": 0.73119588600008, "children": { "run_training.setup": { "total": 0.11323911299996325, "count": 1, "self": 0.11323911299996325 }, "TrainerController.start_learning": { "total": 486.99325768799997, "count": 1, "self": 0.5998248119939262, "children": { "TrainerController._reset_env": { "total": 10.152064672999984, "count": 1, "self": 10.152064672999984 }, "TrainerController.advance": { "total": 475.95804970700607, "count": 18230, "self": 0.2647636390137791, "children": { "env_step": { "total": 475.6932860679923, "count": 18230, "self": 319.6218412549951, "children": { "SubprocessEnvManager._take_step": { "total": 155.80985522799273, "count": 18230, "self": 1.484773808985949, "children": { "TorchPolicy.evaluate": { "total": 154.32508141900678, "count": 18230, "self": 30.601499019009907, "children": { "TorchPolicy.sample_actions": { "total": 123.72358239999687, "count": 18230, "self": 123.72358239999687 } } } } }, "workers": { "total": 0.26158958500445806, "count": 18230, "self": 0.0, "children": { "worker_root": { "total": 485.18984514900376, "count": 18230, "is_parallel": true, "self": 254.91878179300198, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008314743000028102, "count": 1, "is_parallel": true, "self": 0.006455966999965312, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018587760000627895, "count": 10, "is_parallel": true, "self": 0.0018587760000627895 } } }, "UnityEnvironment.step": { "total": 0.05227025199997115, "count": 1, "is_parallel": true, "self": 0.00047612099996285906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031550800002833057, "count": 1, "is_parallel": true, "self": 0.00031550800002833057 }, "communicator.exchange": { "total": 0.04939210300000241, "count": 1, "is_parallel": true, "self": 0.04939210300000241 }, "steps_from_proto": { "total": 0.002086519999977554, "count": 1, "is_parallel": true, "self": 0.0005969019998701697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014896180001073844, "count": 10, "is_parallel": true, "self": 0.0014896180001073844 } } } } } } }, "UnityEnvironment.step": { "total": 230.27106335600178, "count": 18229, "is_parallel": true, "self": 9.58650012498839, "children": { "UnityEnvironment._generate_step_input": { "total": 5.138127000004374, "count": 18229, "is_parallel": true, "self": 5.138127000004374 }, "communicator.exchange": { "total": 184.84432679701166, "count": 18229, "is_parallel": true, "self": 184.84432679701166 }, "steps_from_proto": { "total": 30.70210943399735, "count": 18229, "is_parallel": true, "self": 6.794332392988622, "children": { "_process_rank_one_or_two_observation": { "total": 23.90777704100873, "count": 182290, "is_parallel": true, "self": 23.90777704100873 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015603099996042147, "count": 1, "self": 0.00015603099996042147, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.19481757297785, "count": 351813, "is_parallel": true, "self": 8.943891354005302, "children": { "process_trajectory": { "total": 285.2877351729724, "count": 351813, "is_parallel": true, "self": 283.4051606929725, "children": { "RLTrainer._checkpoint": { "total": 1.882574479999903, "count": 4, "is_parallel": true, "self": 1.882574479999903 } } }, "_update_policy": { "total": 178.96319104600013, "count": 90, "is_parallel": true, "self": 61.57883451900386, "children": { "TorchPPOOptimizer.update": { "total": 117.38435652699627, "count": 4584, "is_parallel": true, "self": 117.38435652699627 } } } } } } } } }, "TrainerController._save_models": { "total": 0.28316246500003217, "count": 1, "self": 0.0014808780000521438, "children": { "RLTrainer._checkpoint": { "total": 0.28168158699998, "count": 1, "self": 0.28168158699998 } } } } } } }