{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4114888906478882, "min": 1.4114805459976196, "max": 1.4281660318374634, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69850.3515625, "min": 68144.109375, "max": 77825.8046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 125.37373737373737, "min": 115.26744186046511, "max": 395.1496062992126, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49648.0, "min": 48974.0, "max": 50304.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999958.0, "min": 49994.0, "max": 1999958.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999958.0, "min": 49994.0, "max": 1999958.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.366734266281128, "min": 0.13362081348896027, "max": 2.6412153244018555, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 937.226806640625, "min": 16.83622169494629, "max": 1098.355224609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4765295475119293, "min": 1.8064354729084742, "max": 3.724425022176762, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1376.705700814724, "min": 227.61086958646774, "max": 1572.8118502497673, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4765295475119293, "min": 1.8064354729084742, "max": 3.724425022176762, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1376.705700814724, "min": 227.61086958646774, "max": 1572.8118502497673, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017633793632073017, "min": 0.014042495858060042, "max": 0.02018553333473392, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052901380896219055, "min": 0.028084991716120083, "max": 0.05643115645846895, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.059039465627736515, "min": 0.025363929911206166, "max": 0.0770965409361654, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17711839688320954, "min": 0.05072785982241233, "max": 0.2312896228084962, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3024488992166655e-06, "min": 3.3024488992166655e-06, "max": 0.00029534482655172497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.907346697649996e-06, "min": 9.907346697649996e-06, "max": 0.0008443971185342999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110078333333335, "min": 0.10110078333333335, "max": 0.19844827500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30330235000000005, "min": 0.20737180000000005, "max": 0.5814657, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.49290883333333e-05, "min": 6.49290883333333e-05, "max": 0.0049225689224999996, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001947872649999999, "min": 0.0001947872649999999, "max": 0.014075138430000002, "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": "1737361946", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=HuggyMo --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737364482" }, "total": 2536.158080883, "count": 1, "self": 0.48998528800029817, "children": { "run_training.setup": { "total": 0.025833106000050066, "count": 1, "self": 0.025833106000050066 }, "TrainerController.start_learning": { "total": 2535.6422624889997, "count": 1, "self": 4.5292568570203, "children": { "TrainerController._reset_env": { "total": 2.999055889000033, "count": 1, "self": 2.999055889000033 }, "TrainerController.advance": { "total": 2527.9950897459794, "count": 229847, "self": 4.623809091019211, "children": { "env_step": { "total": 2016.0948947480092, "count": 229847, "self": 1586.3865760401673, "children": { "SubprocessEnvManager._take_step": { "total": 426.8988296109243, "count": 229847, "self": 16.058900279812974, "children": { "TorchPolicy.evaluate": { "total": 410.8399293311113, "count": 222826, "self": 410.8399293311113 } } }, "workers": { "total": 2.809489096917673, "count": 229847, "self": 0.0, "children": { "worker_root": { "total": 2528.406222538939, "count": 229847, "is_parallel": true, "self": 1234.652959241887, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009786040000108187, "count": 1, "is_parallel": true, "self": 0.0002896690000397939, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006889349999710248, "count": 2, "is_parallel": true, "self": 0.0006889349999710248 } } }, "UnityEnvironment.step": { "total": 0.03409517299996878, "count": 1, "is_parallel": true, "self": 0.00031515999990006094, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002013210000768595, "count": 1, "is_parallel": true, "self": 0.0002013210000768595 }, "communicator.exchange": { "total": 0.032748732999948515, "count": 1, "is_parallel": true, "self": 0.032748732999948515 }, "steps_from_proto": { "total": 0.0008299590000433454, "count": 1, "is_parallel": true, "self": 0.0001796840001588862, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006502749998844592, "count": 2, "is_parallel": true, "self": 0.0006502749998844592 } } } } } } }, "UnityEnvironment.step": { "total": 1293.753263297052, "count": 229846, "is_parallel": true, "self": 38.540516059101265, "children": { "UnityEnvironment._generate_step_input": { "total": 83.62599953492179, "count": 229846, "is_parallel": true, "self": 83.62599953492179 }, "communicator.exchange": { "total": 1081.5978503760984, "count": 229846, "is_parallel": true, "self": 1081.5978503760984 }, "steps_from_proto": { "total": 89.98889732693033, "count": 229846, "is_parallel": true, "self": 31.610869027841318, "children": { "_process_rank_one_or_two_observation": { "total": 58.37802829908901, "count": 459692, "is_parallel": true, "self": 58.37802829908901 } } } } } } } } } } }, "trainer_advance": { "total": 507.2763859069512, "count": 229847, "self": 6.975583698986043, "children": { "process_trajectory": { "total": 152.92173319796325, "count": 229847, "self": 151.5285928979622, "children": { "RLTrainer._checkpoint": { "total": 1.3931403000010505, "count": 10, "self": 1.3931403000010505 } } }, "_update_policy": { "total": 347.3790690100019, "count": 97, "self": 278.39120210798876, "children": { "TorchPPOOptimizer.update": { "total": 68.98786690201314, "count": 2910, "self": 68.98786690201314 } } } } } } }, "trainer_threads": { "total": 8.639999578008428e-07, "count": 1, "self": 8.639999578008428e-07 }, "TrainerController._save_models": { "total": 0.11885913300011453, "count": 1, "self": 0.002003870999942592, "children": { "RLTrainer._checkpoint": { "total": 0.11685526200017193, "count": 1, "self": 0.11685526200017193 } } } } } } }