{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0517903566360474, "min": 1.0326725244522095, "max": 2.8731534481048584, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10054.064453125, "min": 10054.064453125, "max": 29550.3828125, "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": 12.62265396118164, "min": 0.3869762718677521, "max": 12.62265396118164, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.41748046875, "min": 75.07339477539062, "max": 2541.66357421875, "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": 0.07393998239251018, "min": 0.060430978977249236, "max": 0.07393998239251018, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2957599295700407, "min": 0.24172391590899694, "max": 0.36259095703979827, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19997587964376984, "min": 0.11360857380079287, "max": 0.2684432808675018, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7999035185750794, "min": 0.45443429520317147, "max": 1.3407220971934937, "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": 24.84090909090909, "min": 3.1818181818181817, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1093.0, "min": 140.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.84090909090909, "min": 3.1818181818181817, "max": 24.84090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1093.0, "min": 140.0, "max": 1356.0, "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": "1685501965", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685502577" }, "total": 612.1180197669999, "count": 1, "self": 0.5387581169998157, "children": { "run_training.setup": { "total": 0.08172107399991546, "count": 1, "self": 0.08172107399991546 }, "TrainerController.start_learning": { "total": 611.4975405760001, "count": 1, "self": 0.8490235000040229, "children": { "TrainerController._reset_env": { "total": 1.3969728409999789, "count": 1, "self": 1.3969728409999789 }, "TrainerController.advance": { "total": 609.1004524399959, "count": 18202, "self": 0.42086852499619454, "children": { "env_step": { "total": 608.6795839149997, "count": 18202, "self": 496.8841518119842, "children": { "SubprocessEnvManager._take_step": { "total": 111.3940497960183, "count": 18202, "self": 2.8818613530083894, "children": { "TorchPolicy.evaluate": { "total": 108.5121884430099, "count": 18202, "self": 108.5121884430099 } } }, "workers": { "total": 0.40138230699722044, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 609.1914151259948, "count": 18202, "is_parallel": true, "self": 267.0981941490061, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009808130999999776, "count": 1, "is_parallel": true, "self": 0.006363382000017737, "children": { "_process_rank_one_or_two_observation": { "total": 0.003444748999982039, "count": 10, "is_parallel": true, "self": 0.003444748999982039 } } }, "UnityEnvironment.step": { "total": 0.09402156299995568, "count": 1, "is_parallel": true, "self": 0.0008033229999000469, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004779570000437161, "count": 1, "is_parallel": true, "self": 0.0004779570000437161 }, "communicator.exchange": { "total": 0.09019510400003128, "count": 1, "is_parallel": true, "self": 0.09019510400003128 }, "steps_from_proto": { "total": 0.002545178999980635, "count": 1, "is_parallel": true, "self": 0.000470308000217301, "children": { "_process_rank_one_or_two_observation": { "total": 0.002074870999763334, "count": 10, "is_parallel": true, "self": 0.002074870999763334 } } } } } } }, "UnityEnvironment.step": { "total": 342.09322097698873, "count": 18201, "is_parallel": true, "self": 14.44836126398934, "children": { "UnityEnvironment._generate_step_input": { "total": 7.785594965002247, "count": 18201, "is_parallel": true, "self": 7.785594965002247 }, "communicator.exchange": { "total": 272.9288173289741, "count": 18201, "is_parallel": true, "self": 272.9288173289741 }, "steps_from_proto": { "total": 46.93044741902304, "count": 18201, "is_parallel": true, "self": 9.294602695051594, "children": { "_process_rank_one_or_two_observation": { "total": 37.635844723971445, "count": 182010, "is_parallel": true, "self": 37.635844723971445 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001692850000836188, "count": 1, "self": 0.0001692850000836188, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 603.6396184730404, "count": 621761, "is_parallel": true, "self": 14.794617325059221, "children": { "process_trajectory": { "total": 321.1452673309807, "count": 621761, "is_parallel": true, "self": 319.1513344279804, "children": { "RLTrainer._checkpoint": { "total": 1.9939329030003137, "count": 4, "is_parallel": true, "self": 1.9939329030003137 } } }, "_update_policy": { "total": 267.6997338170005, "count": 90, "is_parallel": true, "self": 89.63181487399754, "children": { "TorchPPOOptimizer.update": { "total": 178.06791894300295, "count": 4587, "is_parallel": true, "self": 178.06791894300295 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15092251000010037, "count": 1, "self": 0.0010624149999785004, "children": { "RLTrainer._checkpoint": { "total": 0.14986009500012187, "count": 1, "self": 0.14986009500012187 } } } } } } }