{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9841293096542358, "min": 0.9841293096542358, "max": 2.8675825595855713, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9396.466796875, "min": 9396.466796875, "max": 29366.912109375, "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": 13.035981178283691, "min": 0.25849756598472595, "max": 13.035981178283691, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2542.016357421875, "min": 50.14852523803711, "max": 2622.5810546875, "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": 0.06294916326656033, "min": 0.05922060428408668, "max": 0.07723280240915141, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2517966530662413, "min": 0.23688241713634672, "max": 0.3794541572345171, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19348891269342572, "min": 0.11999747259473866, "max": 0.28345565044996784, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7739556507737029, "min": 0.4799898903789546, "max": 1.3548383895380824, "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": 26.227272727272727, "min": 3.2954545454545454, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1154.0, "min": 145.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.227272727272727, "min": 3.2954545454545454, "max": 26.227272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1154.0, "min": 145.0, "max": 1411.0, "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": "1681596118", "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": "1681596608" }, "total": 489.82899245, "count": 1, "self": 0.3835768090000329, "children": { "run_training.setup": { "total": 0.10941621799997847, "count": 1, "self": 0.10941621799997847 }, "TrainerController.start_learning": { "total": 489.335999423, "count": 1, "self": 0.5837235399984024, "children": { "TrainerController._reset_env": { "total": 5.03921899300002, "count": 1, "self": 5.03921899300002 }, "TrainerController.advance": { "total": 483.5689481760015, "count": 18201, "self": 0.31131240699517093, "children": { "env_step": { "total": 483.25763576900636, "count": 18201, "self": 352.7501096220185, "children": { "SubprocessEnvManager._take_step": { "total": 130.21221038998885, "count": 18201, "self": 1.960293994987751, "children": { "TorchPolicy.evaluate": { "total": 128.2519163950011, "count": 18201, "self": 128.2519163950011 } } }, "workers": { "total": 0.2953157569990026, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 487.69114707799105, "count": 18201, "is_parallel": true, "self": 225.53418673399563, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004832883999995374, "count": 1, "is_parallel": true, "self": 0.0033127519999425203, "children": { "_process_rank_one_or_two_observation": { "total": 0.001520132000052854, "count": 10, "is_parallel": true, "self": 0.001520132000052854 } } }, "UnityEnvironment.step": { "total": 0.07619668199998841, "count": 1, "is_parallel": true, "self": 0.0006562250000570202, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004850020000048971, "count": 1, "is_parallel": true, "self": 0.0004850020000048971 }, "communicator.exchange": { "total": 0.07288282099995058, "count": 1, "is_parallel": true, "self": 0.07288282099995058 }, "steps_from_proto": { "total": 0.0021726339999759148, "count": 1, "is_parallel": true, "self": 0.0004674080000768299, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017052259998990849, "count": 10, "is_parallel": true, "self": 0.0017052259998990849 } } } } } } }, "UnityEnvironment.step": { "total": 262.1569603439954, "count": 18200, "is_parallel": true, "self": 10.600664945989479, "children": { "UnityEnvironment._generate_step_input": { "total": 6.013842614007274, "count": 18200, "is_parallel": true, "self": 6.013842614007274 }, "communicator.exchange": { "total": 209.80247991200162, "count": 18200, "is_parallel": true, "self": 209.80247991200162 }, "steps_from_proto": { "total": 35.739972871997054, "count": 18200, "is_parallel": true, "self": 7.164117890017053, "children": { "_process_rank_one_or_two_observation": { "total": 28.57585498198, "count": 182000, "is_parallel": true, "self": 28.57585498198 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017160400000193476, "count": 1, "self": 0.00017160400000193476, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 479.6872643469803, "count": 431814, "is_parallel": true, "self": 11.136604958933447, "children": { "process_trajectory": { "total": 265.6875933930459, "count": 431814, "is_parallel": true, "self": 263.7996954960459, "children": { "RLTrainer._checkpoint": { "total": 1.8878978970000162, "count": 4, "is_parallel": true, "self": 1.8878978970000162 } } }, "_update_policy": { "total": 202.86306599500097, "count": 90, "is_parallel": true, "self": 75.02822650500019, "children": { "TorchPPOOptimizer.update": { "total": 127.83483949000077, "count": 4584, "is_parallel": true, "self": 127.83483949000077 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1439371100000244, "count": 1, "self": 0.0009608440000192786, "children": { "RLTrainer._checkpoint": { "total": 0.14297626600000513, "count": 1, "self": 0.14297626600000513 } } } } } } }