{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.40199875831604, "min": 1.40199875831604, "max": 1.4266724586486816, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70342.484375, "min": 69334.578125, "max": 76595.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 67.74552957359009, "min": 65.88353413654619, "max": 396.8015873015873, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49251.0, "min": 49161.0, "max": 50039.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999960.0, "min": 49373.0, "max": 1999960.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999960.0, "min": 49373.0, "max": 1999960.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.547769546508789, "min": 0.12250949442386627, "max": 2.547769546508789, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1852.228515625, "min": 15.31368637084961, "max": 1871.535400390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.014336197379531, "min": 1.8435282063484193, "max": 4.061707992453215, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2918.422415494919, "min": 230.4410257935524, "max": 2933.584139406681, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.014336197379531, "min": 1.8435282063484193, "max": 4.061707992453215, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2918.422415494919, "min": 230.4410257935524, "max": 2933.584139406681, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018443399071758095, "min": 0.013454068794574899, "max": 0.01988496080868774, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05533019721527428, "min": 0.026908137589149797, "max": 0.05965488242606322, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056507641904883915, "min": 0.02238618644575278, "max": 0.0631189246972402, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16952292571465175, "min": 0.04477237289150556, "max": 0.18464711035291353, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.963298678933333e-06, "min": 3.963298678933333e-06, "max": 0.000295278376573875, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.18898960368e-05, "min": 1.18898960368e-05, "max": 0.0008437893187369001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10132106666666667, "min": 0.10132106666666667, "max": 0.198426125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039632, "min": 0.20777704999999996, "max": 0.5812631, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.592122666666666e-05, "min": 7.592122666666666e-05, "max": 0.004921463637500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022776368, "min": 0.00022776368, "max": 0.014065028690000002, "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": "1765924951", "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=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1765927550" }, "total": 2599.089384699, "count": 1, "self": 0.4327131120003287, "children": { "run_training.setup": { "total": 0.02670557400006146, "count": 1, "self": 0.02670557400006146 }, "TrainerController.start_learning": { "total": 2598.629966013, "count": 1, "self": 4.190997383007925, "children": { "TrainerController._reset_env": { "total": 2.8718329479999056, "count": 1, "self": 2.8718329479999056 }, "TrainerController.advance": { "total": 2591.4743218529925, "count": 233919, "self": 4.428214881941585, "children": { "env_step": { "total": 2114.1548626880053, "count": 233919, "self": 1709.9405884480925, "children": { "SubprocessEnvManager._take_step": { "total": 401.4862441370626, "count": 233919, "self": 15.333976610053924, "children": { "TorchPolicy.evaluate": { "total": 386.1522675270087, "count": 222946, "self": 386.1522675270087 } } }, "workers": { "total": 2.7280301028500844, "count": 233919, "self": 0.0, "children": { "worker_root": { "total": 2586.1640652170418, "count": 233919, "is_parallel": true, "self": 1200.4449282370103, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009052650000285212, "count": 1, "is_parallel": true, "self": 0.00029925600006208697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006060089999664342, "count": 2, "is_parallel": true, "self": 0.0006060089999664342 } } }, "UnityEnvironment.step": { "total": 0.03702871899997717, "count": 1, "is_parallel": true, "self": 0.0003480980001313583, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020188299993151304, "count": 1, "is_parallel": true, "self": 0.00020188299993151304 }, "communicator.exchange": { "total": 0.03571041599991531, "count": 1, "is_parallel": true, "self": 0.03571041599991531 }, "steps_from_proto": { "total": 0.0007683219999989888, "count": 1, "is_parallel": true, "self": 0.0002202939999733644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005480280000256244, "count": 2, "is_parallel": true, "self": 0.0005480280000256244 } } } } } } }, "UnityEnvironment.step": { "total": 1385.7191369800314, "count": 233918, "is_parallel": true, "self": 38.93191349588483, "children": { "UnityEnvironment._generate_step_input": { "total": 84.66541538704132, "count": 233918, "is_parallel": true, "self": 84.66541538704132 }, "communicator.exchange": { "total": 1170.9130143300563, "count": 233918, "is_parallel": true, "self": 1170.9130143300563 }, "steps_from_proto": { "total": 91.20879376704886, "count": 233918, "is_parallel": true, "self": 32.613547689063466, "children": { "_process_rank_one_or_two_observation": { "total": 58.595246077985394, "count": 467836, "is_parallel": true, "self": 58.595246077985394 } } } } } } } } } } }, "trainer_advance": { "total": 472.89124428304547, "count": 233919, "self": 6.294871824003053, "children": { "process_trajectory": { "total": 165.5296099670419, "count": 233919, "self": 164.39573725304183, "children": { "RLTrainer._checkpoint": { "total": 1.1338727140000628, "count": 10, "self": 1.1338727140000628 } } }, "_update_policy": { "total": 301.0667624920005, "count": 97, "self": 239.5496880220029, "children": { "TorchPPOOptimizer.update": { "total": 61.517074469997624, "count": 2910, "self": 61.517074469997624 } } } } } } }, "trainer_threads": { "total": 8.749998414714355e-07, "count": 1, "self": 8.749998414714355e-07 }, "TrainerController._save_models": { "total": 0.09281295399978262, "count": 1, "self": 0.0012892229997305549, "children": { "RLTrainer._checkpoint": { "total": 0.09152373100005207, "count": 1, "self": 0.09152373100005207 } } } } } } }