{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8830499053001404, "min": 0.8830499053001404, "max": 2.8363564014434814, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8353.65234375, "min": 8353.65234375, "max": 29047.125, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.494943618774414, "min": 0.35231834650039673, "max": 4.551549911499023, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 872.0191040039062, "min": 68.34976196289062, "max": 933.0676879882812, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07086453720380431, "min": 0.06118222751159491, "max": 0.07390668374209781, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28345814881521725, "min": 0.24472891004637964, "max": 0.36953341871048906, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15191776302697904, "min": 0.09984713295211003, "max": 0.204265462037395, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6076710521079162, "min": 0.39938853180844014, "max": 1.021327310186975, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.576098084800001e-06, "min": 9.576098084800001e-06, "max": 0.0004891760021647999, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.8304392339200005e-05, "min": 3.8304392339200005e-05, "max": 0.002346880030624, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10287280000000001, "min": 0.10287280000000001, "max": 0.2467528, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41149120000000006, "min": 0.41149120000000006, "max": 1.204064, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00012472048000000002, "min": 0.00012472048000000002, "max": 0.005870328480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004988819200000001, "min": 0.0004988819200000001, "max": 0.0281656224, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.295454545454547, "min": 3.977272727272727, "max": 26.925925925925927, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1157.0, "min": 175.0, "max": 1466.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.295454545454547, "min": 3.977272727272727, "max": 26.925925925925927, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1157.0, "min": 175.0, "max": 1466.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690313695", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690314317" }, "total": 621.5164189680002, "count": 1, "self": 0.43200070200009577, "children": { "run_training.setup": { "total": 0.033739041999979236, "count": 1, "self": 0.033739041999979236 }, "TrainerController.start_learning": { "total": 621.0506792240001, "count": 1, "self": 0.6737347620072569, "children": { "TrainerController._reset_env": { "total": 5.67384476999996, "count": 1, "self": 5.67384476999996 }, "TrainerController.advance": { "total": 614.5530390119931, "count": 22738, "self": 0.31345974999862847, "children": { "env_step": { "total": 614.2395792619944, "count": 22738, "self": 454.9398542560309, "children": { "SubprocessEnvManager._take_step": { "total": 158.96690175699143, "count": 22738, "self": 2.1871552040016695, "children": { "TorchPolicy.evaluate": { "total": 156.77974655298976, "count": 22738, "self": 156.77974655298976 } } }, "workers": { "total": 0.33282324897209037, "count": 22738, "self": 0.0, "children": { "worker_root": { "total": 619.2830480540058, "count": 22738, "is_parallel": true, "self": 319.96236680498885, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005673337000075662, "count": 1, "is_parallel": true, "self": 0.004224591000024702, "children": { "_process_rank_one_or_two_observation": { "total": 0.00144874600005096, "count": 10, "is_parallel": true, "self": 0.00144874600005096 } } }, "UnityEnvironment.step": { "total": 0.1072800819999884, "count": 1, "is_parallel": true, "self": 0.0006938720001699039, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004352419999804624, "count": 1, "is_parallel": true, "self": 0.0004352419999804624 }, "communicator.exchange": { "total": 0.09662953599990942, "count": 1, "is_parallel": true, "self": 0.09662953599990942 }, "steps_from_proto": { "total": 0.009521431999928609, "count": 1, "is_parallel": true, "self": 0.000582818999760093, "children": { "_process_rank_one_or_two_observation": { "total": 0.008938613000168516, "count": 10, "is_parallel": true, "self": 0.008938613000168516 } } } } } } }, "UnityEnvironment.step": { "total": 299.32068124901696, "count": 22737, "is_parallel": true, "self": 12.83199773403237, "children": { "UnityEnvironment._generate_step_input": { "total": 6.339988543991467, "count": 22737, "is_parallel": true, "self": 6.339988543991467 }, "communicator.exchange": { "total": 237.39019617900829, "count": 22737, "is_parallel": true, "self": 237.39019617900829 }, "steps_from_proto": { "total": 42.758498791984834, "count": 22737, "is_parallel": true, "self": 8.021104299062017, "children": { "_process_rank_one_or_two_observation": { "total": 34.73739449292282, "count": 227370, "is_parallel": true, "self": 34.73739449292282 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.163799985690275e-05, "count": 1, "self": 4.163799985690275e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 609.8191189909913, "count": 528219, "is_parallel": true, "self": 12.488785186972336, "children": { "process_trajectory": { "total": 308.2654576610191, "count": 528219, "is_parallel": true, "self": 306.75806757601924, "children": { "RLTrainer._checkpoint": { "total": 1.5073900849998836, "count": 5, "is_parallel": true, "self": 1.5073900849998836 } } }, "_update_policy": { "total": 289.0648761429999, "count": 113, "is_parallel": true, "self": 115.41331219200686, "children": { "TorchPPOOptimizer.update": { "total": 173.65156395099302, "count": 7676, "is_parallel": true, "self": 173.65156395099302 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15001904199993987, "count": 1, "self": 0.0011677549998694303, "children": { "RLTrainer._checkpoint": { "total": 0.14885128700007044, "count": 1, "self": 0.14885128700007044 } } } } } } }