{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4014153480529785, "min": 1.4014153480529785, "max": 1.425142526626587, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70464.5625, "min": 68280.28125, "max": 78825.75, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.60450160771704, "min": 72.55571847507332, "max": 383.19083969465646, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49514.0, "min": 49048.0, "max": 50198.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49809.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49809.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.457686185836792, "min": 0.09975236654281616, "max": 2.5221385955810547, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1526.22314453125, "min": 12.96780776977539, "max": 1627.763671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7786466425551692, "min": 1.7660236668128233, "max": 4.05224237580822, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2346.53956502676, "min": 229.58307668566704, "max": 2581.3523367643356, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7786466425551692, "min": 1.7660236668128233, "max": 4.05224237580822, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2346.53956502676, "min": 229.58307668566704, "max": 2581.3523367643356, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015355786049217892, "min": 0.013287628344793726, "max": 0.02126010176434647, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04606735814765368, "min": 0.02657525668958745, "max": 0.056038522940070834, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05891480942567189, "min": 0.022040133488674958, "max": 0.06478350590914488, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17674442827701567, "min": 0.044080266977349916, "max": 0.1845672270903985, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.785198738299997e-06, "min": 3.785198738299997e-06, "max": 0.00029535285154904994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1355596214899991e-05, "min": 1.1355596214899991e-05, "max": 0.0008443716185427998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012617, "min": 0.1012617, "max": 0.19845094999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037851, "min": 0.20765400000000006, "max": 0.5814572, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.295882999999995e-05, "min": 7.295882999999995e-05, "max": 0.004922702405, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021887648999999987, "min": 0.00021887648999999987, "max": 0.014074714279999997, "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": "1678270393", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678272846" }, "total": 2452.930687726, "count": 1, "self": 0.44855799400011165, "children": { "run_training.setup": { "total": 0.1169941990000325, "count": 1, "self": 0.1169941990000325 }, "TrainerController.start_learning": { "total": 2452.365135533, "count": 1, "self": 4.320131667011992, "children": { "TrainerController._reset_env": { "total": 9.872488541999985, "count": 1, "self": 9.872488541999985 }, "TrainerController.advance": { "total": 2438.0604559189874, "count": 233000, "self": 4.637487230934767, "children": { "env_step": { "total": 1891.3570427779748, "count": 233000, "self": 1586.9767751369398, "children": { "SubprocessEnvManager._take_step": { "total": 301.55376623407295, "count": 233000, "self": 16.27611722898473, "children": { "TorchPolicy.evaluate": { "total": 285.2776490050882, "count": 223043, "self": 71.1004356171008, "children": { "TorchPolicy.sample_actions": { "total": 214.17721338798742, "count": 223043, "self": 214.17721338798742 } } } } }, "workers": { "total": 2.826501406962052, "count": 233000, "self": 0.0, "children": { "worker_root": { "total": 2443.8941267739915, "count": 233000, "is_parallel": true, "self": 1152.1596722330853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009669599999710954, "count": 1, "is_parallel": true, "self": 0.00033978900000875, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006271709999623454, "count": 2, "is_parallel": true, "self": 0.0006271709999623454 } } }, "UnityEnvironment.step": { "total": 0.05082217099999298, "count": 1, "is_parallel": true, "self": 0.00030833400001029077, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022362599997904908, "count": 1, "is_parallel": true, "self": 0.00022362599997904908 }, "communicator.exchange": { "total": 0.049549022999997305, "count": 1, "is_parallel": true, "self": 0.049549022999997305 }, "steps_from_proto": { "total": 0.000741188000006332, "count": 1, "is_parallel": true, "self": 0.00023918800002320495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005019999999831271, "count": 2, "is_parallel": true, "self": 0.0005019999999831271 } } } } } } }, "UnityEnvironment.step": { "total": 1291.7344545409062, "count": 232999, "is_parallel": true, "self": 38.83175269781873, "children": { "UnityEnvironment._generate_step_input": { "total": 81.42324352493671, "count": 232999, "is_parallel": true, "self": 81.42324352493671 }, "communicator.exchange": { "total": 1078.96576714906, "count": 232999, "is_parallel": true, "self": 1078.96576714906 }, "steps_from_proto": { "total": 92.51369116909075, "count": 232999, "is_parallel": true, "self": 37.21313517305509, "children": { "_process_rank_one_or_two_observation": { "total": 55.300555996035655, "count": 465998, "is_parallel": true, "self": 55.300555996035655 } } } } } } } } } } }, "trainer_advance": { "total": 542.065925910078, "count": 233000, "self": 6.347754026025882, "children": { "process_trajectory": { "total": 171.2920907820511, "count": 233000, "self": 170.04672906705116, "children": { "RLTrainer._checkpoint": { "total": 1.2453617149999445, "count": 10, "self": 1.2453617149999445 } } }, "_update_policy": { "total": 364.42608110200104, "count": 97, "self": 305.4959941900055, "children": { "TorchPPOOptimizer.update": { "total": 58.930086911995545, "count": 2910, "self": 58.930086911995545 } } } } } } }, "trainer_threads": { "total": 8.980000529845711e-07, "count": 1, "self": 8.980000529845711e-07 }, "TrainerController._save_models": { "total": 0.11205850700025621, "count": 1, "self": 0.0020696910005426616, "children": { "RLTrainer._checkpoint": { "total": 0.10998881599971355, "count": 1, "self": 0.10998881599971355 } } } } } } }