{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9016520380973816, "min": 0.9016520380973816, "max": 2.8693056106567383, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8608.9736328125, "min": 8608.9736328125, "max": 29416.12109375, "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": 12.826777458190918, "min": 0.3271358013153076, "max": 12.826777458190918, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2501.2216796875, "min": 63.46434783935547, "max": 2589.490234375, "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": 0.07645784874534464, "min": 0.06286412527734486, "max": 0.07645784874534464, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30583139498137857, "min": 0.2637896755911118, "max": 0.3669677871172704, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1878687548725044, "min": 0.0973890304859892, "max": 0.29223428169886273, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7514750194900176, "min": 0.3895561219439568, "max": 1.419357762909403, "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": 25.40909090909091, "min": 2.840909090909091, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1118.0, "min": 125.0, "max": 1379.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.40909090909091, "min": 2.840909090909091, "max": 25.40909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1118.0, "min": 125.0, "max": 1379.0, "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": "1678793473", "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", "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": "1678793941" }, "total": 468.58006868100006, "count": 1, "self": 0.3866525820000106, "children": { "run_training.setup": { "total": 0.10240821000002143, "count": 1, "self": 0.10240821000002143 }, "TrainerController.start_learning": { "total": 468.091007889, "count": 1, "self": 0.5264990209993243, "children": { "TrainerController._reset_env": { "total": 9.646890308000025, "count": 1, "self": 9.646890308000025 }, "TrainerController.advance": { "total": 457.7695896250007, "count": 18201, "self": 0.28168129699594147, "children": { "env_step": { "total": 457.4879083280048, "count": 18201, "self": 326.40866774399575, "children": { "SubprocessEnvManager._take_step": { "total": 130.8090000780017, "count": 18201, "self": 2.332553960997245, "children": { "TorchPolicy.evaluate": { "total": 128.47644611700446, "count": 18201, "self": 128.47644611700446 } } }, "workers": { "total": 0.2702405060073261, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 466.68930709701107, "count": 18201, "is_parallel": true, "self": 224.62918766201454, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049110740000060105, "count": 1, "is_parallel": true, "self": 0.003349884000044767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015611899999612433, "count": 10, "is_parallel": true, "self": 0.0015611899999612433 } } }, "UnityEnvironment.step": { "total": 0.048371696000003794, "count": 1, "is_parallel": true, "self": 0.0005747390000578889, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031268800000816555, "count": 1, "is_parallel": true, "self": 0.00031268800000816555 }, "communicator.exchange": { "total": 0.045541315999969356, "count": 1, "is_parallel": true, "self": 0.045541315999969356 }, "steps_from_proto": { "total": 0.0019429529999683837, "count": 1, "is_parallel": true, "self": 0.0003946899999505149, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015482630000178688, "count": 10, "is_parallel": true, "self": 0.0015482630000178688 } } } } } } }, "UnityEnvironment.step": { "total": 242.06011943499652, "count": 18200, "is_parallel": true, "self": 9.736031111000557, "children": { "UnityEnvironment._generate_step_input": { "total": 5.315822823995461, "count": 18200, "is_parallel": true, "self": 5.315822823995461 }, "communicator.exchange": { "total": 194.61940928600114, "count": 18200, "is_parallel": true, "self": 194.61940928600114 }, "steps_from_proto": { "total": 32.38885621399936, "count": 18200, "is_parallel": true, "self": 6.374146542021492, "children": { "_process_rank_one_or_two_observation": { "total": 26.01470967197787, "count": 182000, "is_parallel": true, "self": 26.01470967197787 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011934899998777837, "count": 1, "self": 0.00011934899998777837, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.07933884606075, "count": 411966, "is_parallel": true, "self": 10.63137609008686, "children": { "process_trajectory": { "total": 254.94461030497376, "count": 411966, "is_parallel": true, "self": 254.19926587497366, "children": { "RLTrainer._checkpoint": { "total": 0.7453444300001024, "count": 4, "is_parallel": true, "self": 0.7453444300001024 } } }, "_update_policy": { "total": 188.50335245100013, "count": 90, "is_parallel": true, "self": 63.16454122299808, "children": { "TorchPPOOptimizer.update": { "total": 125.33881122800204, "count": 4587, "is_parallel": true, "self": 125.33881122800204 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14790958599996884, "count": 1, "self": 0.0009885880000410907, "children": { "RLTrainer._checkpoint": { "total": 0.14692099799992775, "count": 1, "self": 0.14692099799992775 } } } } } } }