{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.46688005328178406, "min": 0.46145811676979065, "max": 0.548062801361084, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4791.58984375, "min": 4390.77392578125, "max": 5577.51953125, "count": 50 }, "SnowballTarget.Step.mean": { "value": 1999944.0, "min": 1509984.0, "max": 1999944.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 1999944.0, "min": 1509984.0, "max": 1999944.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.30431079864502, "min": 13.924019813537598, "max": 14.351710319519043, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2918.079345703125, "min": 2711.312744140625, "max": 2942.005615234375, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06890000453008813, "min": 0.06153105939784105, "max": 0.07687349683150316, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34450002265044066, "min": 0.25084291392019675, "max": 0.364112547010996, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.14710586433317147, "min": 0.13593446288038702, "max": 0.18358633409975572, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7355293216658574, "min": 0.5437378515215481, "max": 0.835933457548712, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.296997567999969e-07, "min": 7.296997567999969e-07, "max": 7.415467528179998e-05, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.648498783999985e-06, "min": 3.648498783999985e-06, "max": 0.00036334837888399996, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10024320000000002, "min": 0.10024320000000002, "max": 0.1247182, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5012160000000001, "min": 0.40295280000000006, "max": 0.621116, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.213567999999995e-05, "min": 2.213567999999995e-05, "max": 0.00124343818, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00011067839999999976, "min": 0.00011067839999999976, "max": 0.006093688400000002, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.327272727272728, "min": 27.020833333333332, "max": 28.477272727272727, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1558.0, "min": 1198.0, "max": 1559.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.327272727272728, "min": 27.020833333333332, "max": 28.477272727272727, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1558.0, "min": 1198.0, "max": 1559.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692965776", "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=SnowballTarget2 --no-graphics --resume", "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": "1692967032" }, "total": 1256.3228092959998, "count": 1, "self": 0.47509459699995205, "children": { "run_training.setup": { "total": 0.0447613159994944, "count": 1, "self": 0.0447613159994944 }, "TrainerController.start_learning": { "total": 1255.8029533830004, "count": 1, "self": 1.442056101005619, "children": { "TrainerController._reset_env": { "total": 4.730609146000461, "count": 1, "self": 4.730609146000461 }, "TrainerController.advance": { "total": 1249.4823890559937, "count": 45477, "self": 0.7374466800038135, "children": { "env_step": { "total": 1248.74494237599, "count": 45477, "self": 911.1786683529326, "children": { "SubprocessEnvManager._take_step": { "total": 336.8326590630595, "count": 45477, "self": 4.573453362008877, "children": { "TorchPolicy.evaluate": { "total": 332.25920570105063, "count": 45477, "self": 332.25920570105063 } } }, "workers": { "total": 0.7336149599977944, "count": 45477, "self": 0.0, "children": { "worker_root": { "total": 1251.7938582959005, "count": 45477, "is_parallel": true, "self": 585.271636632955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019754929999180604, "count": 1, "is_parallel": true, "self": 0.0005514640006367699, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014240289992812905, "count": 10, "is_parallel": true, "self": 0.0014240289992812905 } } }, "UnityEnvironment.step": { "total": 0.07299540999974852, "count": 1, "is_parallel": true, "self": 0.0006748169989805319, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004447620003702468, "count": 1, "is_parallel": true, "self": 0.0004447620003702468 }, "communicator.exchange": { "total": 0.06937806499990984, "count": 1, "is_parallel": true, "self": 0.06937806499990984 }, "steps_from_proto": { "total": 0.0024977660004879, "count": 1, "is_parallel": true, "self": 0.0006389070013028686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018588589991850313, "count": 10, "is_parallel": true, "self": 0.0018588589991850313 } } } } } } }, "UnityEnvironment.step": { "total": 666.5222216629454, "count": 45476, "is_parallel": true, "self": 27.84803703185571, "children": { "UnityEnvironment._generate_step_input": { "total": 13.8533773930194, "count": 45476, "is_parallel": true, "self": 13.8533773930194 }, "communicator.exchange": { "total": 527.5904366399864, "count": 45476, "is_parallel": true, "self": 527.5904366399864 }, "steps_from_proto": { "total": 97.23037059808394, "count": 45476, "is_parallel": true, "self": 17.93557078792037, "children": { "_process_rank_one_or_two_observation": { "total": 79.29479981016357, "count": 454760, "is_parallel": true, "self": 79.29479981016357 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020477300040511182, "count": 1, "self": 0.00020477300040511182, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1238.3293930730097, "count": 1159049, "is_parallel": true, "self": 27.88234454603662, "children": { "process_trajectory": { "total": 673.0375864319767, "count": 1159049, "is_parallel": true, "self": 669.9807408189754, "children": { "RLTrainer._checkpoint": { "total": 3.0568456130013146, "count": 10, "is_parallel": true, "self": 3.0568456130013146 } } }, "_update_policy": { "total": 537.4094620949963, "count": 227, "is_parallel": true, "self": 216.54626846698739, "children": { "TorchPPOOptimizer.update": { "total": 320.86319362800896, "count": 11574, "is_parallel": true, "self": 320.86319362800896 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14769430700016528, "count": 1, "self": 0.0011035859997718944, "children": { "RLTrainer._checkpoint": { "total": 0.1465907210003934, "count": 1, "self": 0.1465907210003934 } } } } } } }