{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4007296562194824, "min": 1.4007245302200317, "max": 1.42682683467865, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70495.921875, "min": 68635.4921875, "max": 76314.796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.18511450381679, "min": 93.48393194706995, "max": 376.03731343283584, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49353.0, "min": 49312.0, "max": 50389.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999942.0, "min": 49992.0, "max": 1999942.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999942.0, "min": 49992.0, "max": 1999942.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.379218578338623, "min": 0.07510479539632797, "max": 2.429328680038452, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1249.0897216796875, "min": 9.988937377929688, "max": 1252.1820068359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6326565474555608, "min": 1.8995193074968524, "max": 3.8991531246137723, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1907.1446874141693, "min": 252.63606789708138, "max": 1975.041937828064, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6326565474555608, "min": 1.8995193074968524, "max": 3.8991531246137723, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1907.1446874141693, "min": 252.63606789708138, "max": 1975.041937828064, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018153851858450153, "min": 0.011709569438698962, "max": 0.019905976105170947, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05446155557535046, "min": 0.023419138877397924, "max": 0.0578829022590071, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05446317079994414, "min": 0.02218009528393547, "max": 0.05878797835773892, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1633895123998324, "min": 0.04436019056787094, "max": 0.17636393507321677, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.217748927449994e-06, "min": 3.217748927449994e-06, "max": 0.0002953193265602249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.653246782349983e-06, "min": 9.653246782349983e-06, "max": 0.0008440552686482499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107255000000002, "min": 0.10107255000000002, "max": 0.19843977500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30321765000000006, "min": 0.2073027, "max": 0.5813517500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.352024499999989e-05, "min": 6.352024499999989e-05, "max": 0.004922144772500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019056073499999966, "min": 0.00019056073499999966, "max": 0.014069452325, "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": "1740543102", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/Huggy.yaml --env=/content/trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740545654" }, "total": 2551.989641497, "count": 1, "self": 0.42454461099987384, "children": { "run_training.setup": { "total": 0.021144205999917176, "count": 1, "self": 0.021144205999917176 }, "TrainerController.start_learning": { "total": 2551.54395268, "count": 1, "self": 4.824497485160464, "children": { "TrainerController._reset_env": { "total": 2.035489441999971, "count": 1, "self": 2.035489441999971 }, "TrainerController.advance": { "total": 2544.5563250408404, "count": 231529, "self": 4.982795750002879, "children": { "env_step": { "total": 2060.1156394389673, "count": 231529, "self": 1606.9472354351685, "children": { "SubprocessEnvManager._take_step": { "total": 450.34175229187963, "count": 231529, "self": 16.457478940831834, "children": { "TorchPolicy.evaluate": { "total": 433.8842733510478, "count": 222929, "self": 433.8842733510478 } } }, "workers": { "total": 2.826651711919112, "count": 231529, "self": 0.0, "children": { "worker_root": { "total": 2543.642062052013, "count": 231529, "is_parallel": true, "self": 1237.4590170409886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009782659999473253, "count": 1, "is_parallel": true, "self": 0.0002769139998690662, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007013520000782592, "count": 2, "is_parallel": true, "self": 0.0007013520000782592 } } }, "UnityEnvironment.step": { "total": 0.030106870000054187, "count": 1, "is_parallel": true, "self": 0.00028316099997027777, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020373999996081693, "count": 1, "is_parallel": true, "self": 0.00020373999996081693 }, "communicator.exchange": { "total": 0.028744584000151008, "count": 1, "is_parallel": true, "self": 0.028744584000151008 }, "steps_from_proto": { "total": 0.0008753849999720842, "count": 1, "is_parallel": true, "self": 0.00023869799997555674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006366869999965274, "count": 2, "is_parallel": true, "self": 0.0006366869999965274 } } } } } } }, "UnityEnvironment.step": { "total": 1306.1830450110244, "count": 231528, "is_parallel": true, "self": 37.93420653396083, "children": { "UnityEnvironment._generate_step_input": { "total": 87.27523834703106, "count": 231528, "is_parallel": true, "self": 87.27523834703106 }, "communicator.exchange": { "total": 1090.7206668829867, "count": 231528, "is_parallel": true, "self": 1090.7206668829867 }, "steps_from_proto": { "total": 90.2529332470458, "count": 231528, "is_parallel": true, "self": 33.86237911202193, "children": { "_process_rank_one_or_two_observation": { "total": 56.390554135023876, "count": 463056, "is_parallel": true, "self": 56.390554135023876 } } } } } } } } } } }, "trainer_advance": { "total": 479.4578898518705, "count": 231529, "self": 7.155361459779215, "children": { "process_trajectory": { "total": 169.54107003409104, "count": 231529, "self": 168.27271539809158, "children": { "RLTrainer._checkpoint": { "total": 1.268354635999458, "count": 10, "self": 1.268354635999458 } } }, "_update_policy": { "total": 302.76145835800025, "count": 97, "self": 237.46112066699015, "children": { "TorchPPOOptimizer.update": { "total": 65.3003376910101, "count": 2910, "self": 65.3003376910101 } } } } } } }, "trainer_threads": { "total": 1.0639996617101133e-06, "count": 1, "self": 1.0639996617101133e-06 }, "TrainerController._save_models": { "total": 0.12763964799978567, "count": 1, "self": 0.0019152489994667121, "children": { "RLTrainer._checkpoint": { "total": 0.12572439900031895, "count": 1, "self": 0.12572439900031895 } } } } } } }