{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.400522232055664, "min": 1.400522232055664, "max": 1.4246525764465332, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70947.65625, "min": 68268.96875, "max": 76446.3828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.27777777777777, "min": 74.91019786910198, "max": 386.6744186046512, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49467.0, "min": 49216.0, "max": 50121.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49390.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49390.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.520679235458374, "min": -0.030191652476787567, "max": 2.5252561569213867, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1497.283447265625, "min": -3.8645315170288086, "max": 1611.303466796875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9384924755353317, "min": 1.7742026192136109, "max": 4.086035496741533, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2339.464530467987, "min": 227.0979352593422, "max": 2515.6682626605034, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9384924755353317, "min": 1.7742026192136109, "max": 4.086035496741533, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2339.464530467987, "min": 227.0979352593422, "max": 2515.6682626605034, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014587482059788373, "min": 0.01224293897232403, "max": 0.019772576961743955, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.043762446179365116, "min": 0.028223829158135535, "max": 0.059317730885231866, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05838844267030557, "min": 0.024509355798363684, "max": 0.06113586419572433, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1751653280109167, "min": 0.04901871159672737, "max": 0.1751653280109167, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5457988181000064e-06, "min": 3.5457988181000064e-06, "max": 0.0002952987015670999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0637396454300019e-05, "min": 1.0637396454300019e-05, "max": 0.00084388846870385, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1011819, "min": 0.1011819, "max": 0.19843290000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30354570000000003, "min": 0.20751670000000005, "max": 0.5812961499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.897681000000012e-05, "min": 6.897681000000012e-05, "max": 0.00492180171, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020693043000000037, "min": 0.00020693043000000037, "max": 0.014066677885000003, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690833372", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1690835865" }, "total": 2492.7002274730003, "count": 1, "self": 0.43571845600035886, "children": { "run_training.setup": { "total": 0.05658021299996108, "count": 1, "self": 0.05658021299996108 }, "TrainerController.start_learning": { "total": 2492.207928804, "count": 1, "self": 4.700460900102826, "children": { "TrainerController._reset_env": { "total": 6.205851712000026, "count": 1, "self": 6.205851712000026 }, "TrainerController.advance": { "total": 2481.1809644808973, "count": 233134, "self": 4.57181164296162, "children": { "env_step": { "total": 1910.4149071500399, "count": 233134, "self": 1613.778646739961, "children": { "SubprocessEnvManager._take_step": { "total": 293.6753267180569, "count": 233134, "self": 16.730116832093813, "children": { "TorchPolicy.evaluate": { "total": 276.9452098859631, "count": 222984, "self": 276.9452098859631 } } }, "workers": { "total": 2.9609336920219675, "count": 233134, "self": 0.0, "children": { "worker_root": { "total": 2484.6013086620173, "count": 233134, "is_parallel": true, "self": 1170.0369470519709, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001027229999976953, "count": 1, "is_parallel": true, "self": 0.00026444399998126755, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007627859999956854, "count": 2, "is_parallel": true, "self": 0.0007627859999956854 } } }, "UnityEnvironment.step": { "total": 0.03036963299996387, "count": 1, "is_parallel": true, "self": 0.00031811799988190614, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002239780000081737, "count": 1, "is_parallel": true, "self": 0.0002239780000081737 }, "communicator.exchange": { "total": 0.029092485000091983, "count": 1, "is_parallel": true, "self": 0.029092485000091983 }, "steps_from_proto": { "total": 0.0007350519999818061, "count": 1, "is_parallel": true, "self": 0.00021101400000134163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005240379999804645, "count": 2, "is_parallel": true, "self": 0.0005240379999804645 } } } } } } }, "UnityEnvironment.step": { "total": 1314.5643616100465, "count": 233133, "is_parallel": true, "self": 39.452957163971405, "children": { "UnityEnvironment._generate_step_input": { "total": 81.18107158696785, "count": 233133, "is_parallel": true, "self": 81.18107158696785 }, "communicator.exchange": { "total": 1097.3132756051086, "count": 233133, "is_parallel": true, "self": 1097.3132756051086 }, "steps_from_proto": { "total": 96.61705725399861, "count": 233133, "is_parallel": true, "self": 34.95878281099169, "children": { "_process_rank_one_or_two_observation": { "total": 61.65827444300692, "count": 466266, "is_parallel": true, "self": 61.65827444300692 } } } } } } } } } } }, "trainer_advance": { "total": 566.1942456878955, "count": 233134, "self": 6.8686287619603945, "children": { "process_trajectory": { "total": 143.3344130229367, "count": 233134, "self": 142.0489793959365, "children": { "RLTrainer._checkpoint": { "total": 1.2854336270002023, "count": 10, "self": 1.2854336270002023 } } }, "_update_policy": { "total": 415.99120390299845, "count": 97, "self": 355.4839344480147, "children": { "TorchPPOOptimizer.update": { "total": 60.50726945498377, "count": 2910, "self": 60.50726945498377 } } } } } } }, "trainer_threads": { "total": 1.2850000530306716e-06, "count": 1, "self": 1.2850000530306716e-06 }, "TrainerController._save_models": { "total": 0.12065042599988374, "count": 1, "self": 0.0019035649997931614, "children": { "RLTrainer._checkpoint": { "total": 0.11874686100009058, "count": 1, "self": 0.11874686100009058 } } } } } } }