{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.8118195533752441, "min": 1.8118195533752441, "max": 2.771235704421997, "count": 24 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17378.97265625, "min": 16125.8203125, "max": 27430.41796875, "count": 24 }, "SnowballTarget.Step.mean": { "value": 299960.0, "min": 69992.0, "max": 299960.0, "count": 24 }, "SnowballTarget.Step.sum": { "value": 299960.0, "min": 69992.0, "max": 299960.0, "count": 24 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.524247169494629, "min": 1.3393324613571167, "max": 8.524247169494629, "count": 24 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 835.376220703125, "min": 62.94862747192383, "max": 854.62353515625, "count": 24 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 24 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 4378.0, "max": 10945.0, "count": 24 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 19.608695652173914, "min": 7.2727272727272725, "max": 20.5, "count": 24 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 902.0, "min": 160.0, "max": 1069.0, "count": 24 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 19.608695652173914, "min": 7.2727272727272725, "max": 20.5, "count": 24 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 902.0, "min": 160.0, "max": 1069.0, "count": 24 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 24 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.046152475377773894, "min": 0.045261845252724246, "max": 0.05613040942273709, "count": 21 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.046152475377773894, "min": 0.045261845252724246, "max": 0.05613040942273709, "count": 21 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2707705969611804, "min": 0.2489233562161052, "max": 0.31760141750176746, "count": 21 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2707705969611804, "min": 0.2489233562161052, "max": 0.31760141750176746, "count": 21 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.056098471999992e-06, "min": 3.056098471999992e-06, "max": 0.00014962669185333328, "count": 21 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.056098471999992e-06, "min": 3.056098471999992e-06, "max": 0.00014962669185333328, "count": 21 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10152800000000005, "min": 0.10152800000000005, "max": 0.1748133333333333, "count": 21 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10152800000000005, "min": 0.10152800000000005, "max": 0.1748133333333333, "count": 21 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00016264719999999966, "min": 0.00016264719999999966, "max": 0.007483852, "count": 21 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00016264719999999966, "min": 0.00016264719999999966, "max": 0.007483852, "count": 21 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1720249497", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720250049" }, "total": 552.2202583549999, "count": 1, "self": 0.42978697499984264, "children": { "run_training.setup": { "total": 0.05920954599992001, "count": 1, "self": 0.05920954599992001 }, "TrainerController.start_learning": { "total": 551.7312618340002, "count": 1, "self": 0.7641373830313114, "children": { "TrainerController._reset_env": { "total": 2.0999622650001584, "count": 1, "self": 2.0999622650001584 }, "TrainerController.advance": { "total": 548.7307076829686, "count": 21407, "self": 0.3434664609551419, "children": { "env_step": { "total": 548.3872412220135, "count": 21407, "self": 357.6078869710309, "children": { "SubprocessEnvManager._take_step": { "total": 190.41055164898262, "count": 21407, "self": 1.8487056709798253, "children": { "TorchPolicy.evaluate": { "total": 188.5618459780028, "count": 21407, "self": 188.5618459780028 } } }, "workers": { "total": 0.36880260199995973, "count": 21407, "self": 0.0, "children": { "worker_root": { "total": 550.1251846769994, "count": 21407, "is_parallel": true, "self": 269.83681195401164, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026616340001055505, "count": 1, "is_parallel": true, "self": 0.0008052370003497344, "children": { "_process_rank_one_or_two_observation": { "total": 0.001856396999755816, "count": 10, "is_parallel": true, "self": 0.001856396999755816 } } }, "UnityEnvironment.step": { "total": 0.045671846000004734, "count": 1, "is_parallel": true, "self": 0.000765755999736939, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000451747000170144, "count": 1, "is_parallel": true, "self": 0.000451747000170144 }, "communicator.exchange": { "total": 0.04220969600009994, "count": 1, "is_parallel": true, "self": 0.04220969600009994 }, "steps_from_proto": { "total": 0.0022446469999977126, "count": 1, "is_parallel": true, "self": 0.0004208880002352089, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018237589997625037, "count": 10, "is_parallel": true, "self": 0.0018237589997625037 } } } } } } }, "UnityEnvironment.step": { "total": 280.2883727229878, "count": 21406, "is_parallel": true, "self": 12.630060233967242, "children": { "UnityEnvironment._generate_step_input": { "total": 6.792817600001172, "count": 21406, "is_parallel": true, "self": 6.792817600001172 }, "communicator.exchange": { "total": 218.07006982201506, "count": 21406, "is_parallel": true, "self": 218.07006982201506 }, "steps_from_proto": { "total": 42.79542506700432, "count": 21406, "is_parallel": true, "self": 8.107294056017963, "children": { "_process_rank_one_or_two_observation": { "total": 34.68813101098635, "count": 214060, "is_parallel": true, "self": 34.68813101098635 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00023989800001800177, "count": 1, "self": 0.00023989800001800177, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 539.1018590201095, "count": 1085599, "is_parallel": true, "self": 24.56119199611271, "children": { "process_trajectory": { "total": 362.60708646899616, "count": 1085599, "is_parallel": true, "self": 361.4931656489964, "children": { "RLTrainer._checkpoint": { "total": 1.1139208199997483, "count": 5, "is_parallel": true, "self": 1.1139208199997483 } } }, "_update_policy": { "total": 151.93358055500062, "count": 21, "is_parallel": true, "self": 69.69792452899833, "children": { "TorchPPOOptimizer.update": { "total": 82.23565602600229, "count": 2640, "is_parallel": true, "self": 82.23565602600229 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13621460500007743, "count": 1, "self": 0.0026471169999240374, "children": { "RLTrainer._checkpoint": { "total": 0.1335674880001534, "count": 1, "self": 0.1335674880001534 } } } } } } }