{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4099103212356567, "min": 1.4099103212356567, "max": 1.427646279335022, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69168.7890625, "min": 68413.328125, "max": 77026.0625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.70961887477314, "min": 81.81426202321725, "max": 401.69354838709677, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49430.0, "min": 49065.0, "max": 50362.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999992.0, "min": 49739.0, "max": 1999992.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999992.0, "min": 49739.0, "max": 1999992.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4572455883026123, "min": 0.09462294727563858, "max": 2.4802956581115723, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1353.9423828125, "min": 11.922491073608398, "max": 1439.9947509765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7513251617253367, "min": 1.6300948581525259, "max": 4.0355168117893685, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2066.9801641106606, "min": 205.39195212721825, "max": 2332.9043413996696, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7513251617253367, "min": 1.6300948581525259, "max": 4.0355168117893685, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2066.9801641106606, "min": 205.39195212721825, "max": 2332.9043413996696, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0154298917110686, "min": 0.013674162442233259, "max": 0.021218481025425718, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.046289675133205796, "min": 0.027996460537542588, "max": 0.05632714456442045, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0559297372897466, "min": 0.022904504214723904, "max": 0.060283168156941735, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1677892118692398, "min": 0.04580900842944781, "max": 0.17607355316480003, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.485898838066673e-06, "min": 3.485898838066673e-06, "max": 0.0002953408515530499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.045769651420002e-05, "min": 1.045769651420002e-05, "max": 0.0008440114686628498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116193333333333, "min": 0.10116193333333333, "max": 0.19844695000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034858, "min": 0.20750990000000005, "max": 0.58133715, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.798047333333343e-05, "min": 6.798047333333343e-05, "max": 0.004922502805000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002039414200000003, "min": 0.0002039414200000003, "max": 0.014068723785000002, "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": "1692889643", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.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": "1692892046" }, "total": 2402.791256319, "count": 1, "self": 0.3930857259997538, "children": { "run_training.setup": { "total": 0.043737222000004294, "count": 1, "self": 0.043737222000004294 }, "TrainerController.start_learning": { "total": 2402.354433371, "count": 1, "self": 4.261773717054439, "children": { "TrainerController._reset_env": { "total": 4.19523039500001, "count": 1, "self": 4.19523039500001 }, "TrainerController.advance": { "total": 2393.7487286719456, "count": 232389, "self": 4.418012495007588, "children": { "env_step": { "total": 1843.068237371946, "count": 232389, "self": 1558.8332039299614, "children": { "SubprocessEnvManager._take_step": { "total": 281.3663178799254, "count": 232389, "self": 16.168208901921446, "children": { "TorchPolicy.evaluate": { "total": 265.198108978004, "count": 222906, "self": 265.198108978004 } } }, "workers": { "total": 2.868715562059151, "count": 232389, "self": 0.0, "children": { "worker_root": { "total": 2394.8874300529856, "count": 232389, "is_parallel": true, "self": 1120.1045106100626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008883439999749498, "count": 1, "is_parallel": true, "self": 0.00025376399992182996, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006345800000531199, "count": 2, "is_parallel": true, "self": 0.0006345800000531199 } } }, "UnityEnvironment.step": { "total": 0.028447797000012542, "count": 1, "is_parallel": true, "self": 0.00037317999999686435, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019975700001850782, "count": 1, "is_parallel": true, "self": 0.00019975700001850782 }, "communicator.exchange": { "total": 0.02707186200001388, "count": 1, "is_parallel": true, "self": 0.02707186200001388 }, "steps_from_proto": { "total": 0.0008029979999832904, "count": 1, "is_parallel": true, "self": 0.00021843500002205474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005845629999612356, "count": 2, "is_parallel": true, "self": 0.0005845629999612356 } } } } } } }, "UnityEnvironment.step": { "total": 1274.782919442923, "count": 232388, "is_parallel": true, "self": 39.91974674208518, "children": { "UnityEnvironment._generate_step_input": { "total": 80.43331125986748, "count": 232388, "is_parallel": true, "self": 80.43331125986748 }, "communicator.exchange": { "total": 1057.5923567569598, "count": 232388, "is_parallel": true, "self": 1057.5923567569598 }, "steps_from_proto": { "total": 96.83750468401047, "count": 232388, "is_parallel": true, "self": 34.24404730799347, "children": { "_process_rank_one_or_two_observation": { "total": 62.593457376017, "count": 464776, "is_parallel": true, "self": 62.593457376017 } } } } } } } } } } }, "trainer_advance": { "total": 546.2624788049918, "count": 232389, "self": 6.764582175953933, "children": { "process_trajectory": { "total": 137.15358938103918, "count": 232389, "self": 135.75129072203924, "children": { "RLTrainer._checkpoint": { "total": 1.402298658999939, "count": 10, "self": 1.402298658999939 } } }, "_update_policy": { "total": 402.3443072479987, "count": 97, "self": 341.7335568399899, "children": { "TorchPPOOptimizer.update": { "total": 60.61075040800881, "count": 2910, "self": 60.61075040800881 } } } } } } }, "trainer_threads": { "total": 1.321999661740847e-06, "count": 1, "self": 1.321999661740847e-06 }, "TrainerController._save_models": { "total": 0.14869926500023212, "count": 1, "self": 0.0019198760001017945, "children": { "RLTrainer._checkpoint": { "total": 0.14677938900013032, "count": 1, "self": 0.14677938900013032 } } } } } } }