{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.2307606935501099, "min": 1.225938081741333, "max": 2.871253252029419, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10925.462890625, "min": 10925.462890625, "max": 30576.9140625, "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": 10.024139404296875, "min": 0.6596857905387878, "max": 10.024139404296875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1954.707275390625, "min": 127.97904205322266, "max": 2036.6676025390625, "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": 0.41822737135807986, "min": 0.38008801330528924, "max": 0.45904111270566417, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 2.091136856790399, "min": 1.9525918932049535, "max": 3.1637092345445126, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22286204343351224, "min": 0.11132878102847218, "max": 0.26329253201321184, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1143102171675612, "min": 0.556643905142361, "max": 1.6179094727073484, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.672897442400007e-06, "min": 7.672897442400007e-06, "max": 0.0002921592026136, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.8364487212000034e-05, "min": 3.8364487212000034e-05, "max": 0.0019419960526679996, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.1025576, "min": 0.1025576, "max": 0.19738640000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.512788, "min": 0.512788, "max": 1.347332, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001376242400000001, "min": 0.0001376242400000001, "max": 0.00486958136, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006881212000000006, "min": 0.0006881212000000006, "max": 0.0323718668, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.15909090909091, "min": 2.659090909090909, "max": 21.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 931.0, "min": 117.0, "max": 1106.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.15909090909091, "min": 2.659090909090909, "max": 21.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 931.0, "min": 117.0, "max": 1106.0, "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": "1678895121", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 --force", "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": "1678895577" }, "total": 456.323012178, "count": 1, "self": 0.8432498519998717, "children": { "run_training.setup": { "total": 0.10473651500001324, "count": 1, "self": 0.10473651500001324 }, "TrainerController.start_learning": { "total": 455.3750258110001, "count": 1, "self": 0.5977656499812838, "children": { "TrainerController._reset_env": { "total": 5.664601045999916, "count": 1, "self": 5.664601045999916 }, "TrainerController.advance": { "total": 448.78136185701896, "count": 18230, "self": 0.3036532180171889, "children": { "env_step": { "total": 448.4777086390018, "count": 18230, "self": 315.94792888503935, "children": { "SubprocessEnvManager._take_step": { "total": 132.25188639097246, "count": 18230, "self": 2.0001905579852064, "children": { "TorchPolicy.evaluate": { "total": 130.25169583298725, "count": 18230, "self": 130.25169583298725 } } }, "workers": { "total": 0.27789336298997114, "count": 18230, "self": 0.0, "children": { "worker_root": { "total": 453.7511815229875, "count": 18230, "is_parallel": true, "self": 221.35104357697242, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002017840000007709, "count": 1, "is_parallel": true, "self": 0.0005929110000124638, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014249289999952452, "count": 10, "is_parallel": true, "self": 0.0014249289999952452 } } }, "UnityEnvironment.step": { "total": 0.0345397270000376, "count": 1, "is_parallel": true, "self": 0.00037924200023553567, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038066100000833103, "count": 1, "is_parallel": true, "self": 0.00038066100000833103 }, "communicator.exchange": { "total": 0.031999400999893624, "count": 1, "is_parallel": true, "self": 0.031999400999893624 }, "steps_from_proto": { "total": 0.0017804229999001109, "count": 1, "is_parallel": true, "self": 0.0003476679996765597, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014327550002235512, "count": 10, "is_parallel": true, "self": 0.0014327550002235512 } } } } } } }, "UnityEnvironment.step": { "total": 232.4001379460151, "count": 18229, "is_parallel": true, "self": 9.322493646025578, "children": { "UnityEnvironment._generate_step_input": { "total": 5.0004826440108445, "count": 18229, "is_parallel": true, "self": 5.0004826440108445 }, "communicator.exchange": { "total": 187.4479591879849, "count": 18229, "is_parallel": true, "self": 187.4479591879849 }, "steps_from_proto": { "total": 30.629202467993764, "count": 18229, "is_parallel": true, "self": 6.0556616460596615, "children": { "_process_rank_one_or_two_observation": { "total": 24.573540821934102, "count": 182290, "is_parallel": true, "self": 24.573540821934102 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001668970000991976, "count": 1, "self": 0.0001668970000991976, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 447.3773203830174, "count": 198318, "is_parallel": true, "self": 5.090485086038825, "children": { "process_trajectory": { "total": 179.38022689897866, "count": 198318, "is_parallel": true, "self": 177.60127781797905, "children": { "RLTrainer._checkpoint": { "total": 1.7789490809996096, "count": 4, "is_parallel": true, "self": 1.7789490809996096 } } }, "_update_policy": { "total": 262.9066083979999, "count": 120, "is_parallel": true, "self": 6.559976594988029, "children": { "TorchPPOOptimizer.update": { "total": 256.34663180301186, "count": 5760, "is_parallel": true, "self": 256.34663180301186 } } } } } } } } }, "TrainerController._save_models": { "total": 0.3311303609998504, "count": 1, "self": 0.001850975000024846, "children": { "RLTrainer._checkpoint": { "total": 0.32927938599982554, "count": 1, "self": 0.32927938599982554 } } } } } } }