{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9561145305633545, "min": 0.9561145305633545, "max": 2.8614859580993652, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9139.4990234375, "min": 9139.4990234375, "max": 29304.4765625, "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": 12.528475761413574, "min": 0.49105018377304077, "max": 12.528475761413574, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2443.052734375, "min": 95.26373291015625, "max": 2543.5517578125, "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": 0.0661039645317086, "min": 0.0601040211561257, "max": 0.07650993077504431, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2644158581268344, "min": 0.2404160846245028, "max": 0.38254965387522155, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21723191301320113, "min": 0.1356242573078192, "max": 0.2842186689376831, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8689276520528045, "min": 0.5424970292312769, "max": 1.264439456018747, "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": 24.727272727272727, "min": 3.840909090909091, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1088.0, "min": 169.0, "max": 1378.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.727272727272727, "min": 3.840909090909091, "max": 25.054545454545455, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1088.0, "min": 169.0, "max": 1378.0, "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": "1695762050", "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=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": "1695762558" }, "total": 507.94779145, "count": 1, "self": 0.43602503999994724, "children": { "run_training.setup": { "total": 0.08068588099999374, "count": 1, "self": 0.08068588099999374 }, "TrainerController.start_learning": { "total": 507.43108052900004, "count": 1, "self": 0.6370363209971401, "children": { "TrainerController._reset_env": { "total": 4.784027914999996, "count": 1, "self": 4.784027914999996 }, "TrainerController.advance": { "total": 501.85905988300294, "count": 18202, "self": 0.3109384370046655, "children": { "env_step": { "total": 501.5481214459983, "count": 18202, "self": 365.14232891399325, "children": { "SubprocessEnvManager._take_step": { "total": 136.08933784600734, "count": 18202, "self": 1.900261607015068, "children": { "TorchPolicy.evaluate": { "total": 134.18907623899227, "count": 18202, "self": 134.18907623899227 } } }, "workers": { "total": 0.3164546859976838, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 505.72155496300405, "count": 18202, "is_parallel": true, "self": 235.34943326500292, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005094441000011329, "count": 1, "is_parallel": true, "self": 0.0035507910000092124, "children": { "_process_rank_one_or_two_observation": { "total": 0.001543650000002117, "count": 10, "is_parallel": true, "self": 0.001543650000002117 } } }, "UnityEnvironment.step": { "total": 0.04444959500000323, "count": 1, "is_parallel": true, "self": 0.0006716929999868171, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004314720000024863, "count": 1, "is_parallel": true, "self": 0.0004314720000024863 }, "communicator.exchange": { "total": 0.04020042600001261, "count": 1, "is_parallel": true, "self": 0.04020042600001261 }, "steps_from_proto": { "total": 0.0031460040000013123, "count": 1, "is_parallel": true, "self": 0.00039927099999204074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027467330000092716, "count": 10, "is_parallel": true, "self": 0.0027467330000092716 } } } } } } }, "UnityEnvironment.step": { "total": 270.37212169800114, "count": 18201, "is_parallel": true, "self": 11.338069680007209, "children": { "UnityEnvironment._generate_step_input": { "total": 5.587371680995233, "count": 18201, "is_parallel": true, "self": 5.587371680995233 }, "communicator.exchange": { "total": 215.04351788299445, "count": 18201, "is_parallel": true, "self": 215.04351788299445 }, "steps_from_proto": { "total": 38.403162454004246, "count": 18201, "is_parallel": true, "self": 7.173915816007195, "children": { "_process_rank_one_or_two_observation": { "total": 31.22924663799705, "count": 182010, "is_parallel": true, "self": 31.22924663799705 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012166599992724514, "count": 1, "self": 0.00012166599992724514, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 497.9587996079621, "count": 483737, "is_parallel": true, "self": 10.883326643983537, "children": { "process_trajectory": { "total": 275.4414626869786, "count": 483737, "is_parallel": true, "self": 273.23697505297866, "children": { "RLTrainer._checkpoint": { "total": 2.2044876339999178, "count": 4, "is_parallel": true, "self": 2.2044876339999178 } } }, "_update_policy": { "total": 211.63401027699996, "count": 90, "is_parallel": true, "self": 81.59266272700359, "children": { "TorchPPOOptimizer.update": { "total": 130.04134754999637, "count": 4587, "is_parallel": true, "self": 130.04134754999637 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15083474400000796, "count": 1, "self": 0.0009484439999596361, "children": { "RLTrainer._checkpoint": { "total": 0.14988630000004832, "count": 1, "self": 0.14988630000004832 } } } } } } }