{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.011173129081726, "min": 1.011173129081726, "max": 2.869828224182129, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9654.6806640625, "min": 9654.6806640625, "max": 29389.91015625, "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": 13.04691219329834, "min": 0.1452033817768097, "max": 13.04691219329834, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.14794921875, "min": 28.169456481933594, "max": 2652.7568359375, "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": 0.07259401757448145, "min": 0.060521122377180936, "max": 0.07415633577686237, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2903760702979258, "min": 0.24208448950872374, "max": 0.36980804674642376, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17296158814547108, "min": 0.10918253992898755, "max": 0.2983864552396185, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6918463525818843, "min": 0.4367301597159502, "max": 1.4200462596673593, "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": 25.704545454545453, "min": 2.9545454545454546, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1131.0, "min": 130.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.704545454545453, "min": 2.9545454545454546, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1131.0, "min": 130.0, "max": 1421.0, "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": "1692191764", "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": "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": "1692192261" }, "total": 496.68264148799994, "count": 1, "self": 0.43838204500002576, "children": { "run_training.setup": { "total": 0.06760873600001105, "count": 1, "self": 0.06760873600001105 }, "TrainerController.start_learning": { "total": 496.1766507069999, "count": 1, "self": 0.5557893170071111, "children": { "TrainerController._reset_env": { "total": 5.470743594000055, "count": 1, "self": 5.470743594000055 }, "TrainerController.advance": { "total": 490.0103455019929, "count": 18210, "self": 0.28379086699203526, "children": { "env_step": { "total": 489.72655463500087, "count": 18210, "self": 359.31765245900635, "children": { "SubprocessEnvManager._take_step": { "total": 130.1140061650018, "count": 18210, "self": 1.8180262730057848, "children": { "TorchPolicy.evaluate": { "total": 128.295979891996, "count": 18210, "self": 128.295979891996 } } }, "workers": { "total": 0.2948960109927157, "count": 18210, "self": 0.0, "children": { "worker_root": { "total": 494.5516714570015, "count": 18210, "is_parallel": true, "self": 233.5867412100166, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006838848000029429, "count": 1, "is_parallel": true, "self": 0.00429311199991389, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025457360001155394, "count": 10, "is_parallel": true, "self": 0.0025457360001155394 } } }, "UnityEnvironment.step": { "total": 0.04558289399994919, "count": 1, "is_parallel": true, "self": 0.0006465410000373595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033266399998410634, "count": 1, "is_parallel": true, "self": 0.00033266399998410634 }, "communicator.exchange": { "total": 0.04227061500000673, "count": 1, "is_parallel": true, "self": 0.04227061500000673 }, "steps_from_proto": { "total": 0.002333073999920998, "count": 1, "is_parallel": true, "self": 0.0003918320001048414, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019412419998161567, "count": 10, "is_parallel": true, "self": 0.0019412419998161567 } } } } } } }, "UnityEnvironment.step": { "total": 260.96493024698486, "count": 18209, "is_parallel": true, "self": 11.189107573975662, "children": { "UnityEnvironment._generate_step_input": { "total": 5.4994823900011625, "count": 18209, "is_parallel": true, "self": 5.4994823900011625 }, "communicator.exchange": { "total": 206.9516172590022, "count": 18209, "is_parallel": true, "self": 206.9516172590022 }, "steps_from_proto": { "total": 37.324723024005834, "count": 18209, "is_parallel": true, "self": 6.813653004019784, "children": { "_process_rank_one_or_two_observation": { "total": 30.51107001998605, "count": 182090, "is_parallel": true, "self": 30.51107001998605 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012091199982933176, "count": 1, "self": 0.00012091199982933176, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 486.1855241710417, "count": 468209, "is_parallel": true, "self": 10.4816415440622, "children": { "process_trajectory": { "total": 266.24335595697937, "count": 468209, "is_parallel": true, "self": 265.1423425849795, "children": { "RLTrainer._checkpoint": { "total": 1.1010133719998976, "count": 4, "is_parallel": true, "self": 1.1010133719998976 } } }, "_update_policy": { "total": 209.46052667000015, "count": 90, "is_parallel": true, "self": 83.5181334649941, "children": { "TorchPPOOptimizer.update": { "total": 125.94239320500606, "count": 4587, "is_parallel": true, "self": 125.94239320500606 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13965138200001093, "count": 1, "self": 0.0008730150000246795, "children": { "RLTrainer._checkpoint": { "total": 0.13877836699998625, "count": 1, "self": 0.13877836699998625 } } } } } } }