{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4045052528381348, "min": 1.4045052528381348, "max": 1.4261188507080078, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70524.421875, "min": 67975.828125, "max": 77063.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.06, "min": 72.51541850220265, "max": 400.664, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49439.0, "min": 49153.0, "max": 50083.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49660.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49660.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4857101440429688, "min": 0.09191108494997025, "max": 2.5266377925872803, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1615.711669921875, "min": 11.396974563598633, "max": 1682.56787109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.806710924735436, "min": 1.7156794383641212, "max": 4.037060651463243, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2474.3621010780334, "min": 212.74425035715103, "max": 2620.0523627996445, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.806710924735436, "min": 1.7156794383641212, "max": 4.037060651463243, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2474.3621010780334, "min": 212.74425035715103, "max": 2620.0523627996445, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017556714199518965, "min": 0.013945074096813592, "max": 0.020151792924176938, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052670142598556895, "min": 0.028300921110591543, "max": 0.05697942969078819, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0656424303021696, "min": 0.022101807718475662, "max": 0.0656424303021696, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1969272909065088, "min": 0.044203615436951324, "max": 0.1969272909065088, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7739487420500003e-06, "min": 3.7739487420500003e-06, "max": 0.00029536507654497496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.132184622615e-05, "min": 1.132184622615e-05, "max": 0.0008441845686051499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125795000000003, "min": 0.10125795000000003, "max": 0.19845502499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30377385000000007, "min": 0.2076518, "max": 0.58139485, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.2771705e-05, "min": 7.2771705e-05, "max": 0.004922905747499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021831511500000001, "min": 0.00021831511500000001, "max": 0.014071603015000005, "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": "1738342557", "python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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=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": "1738345059" }, "total": 2502.322451365, "count": 1, "self": 0.49269206999952075, "children": { "run_training.setup": { "total": 0.02311536700005945, "count": 1, "self": 0.02311536700005945 }, "TrainerController.start_learning": { "total": 2501.806643928, "count": 1, "self": 5.039413767939095, "children": { "TrainerController._reset_env": { "total": 3.5671512279999433, "count": 1, "self": 3.5671512279999433 }, "TrainerController.advance": { "total": 2493.0881446740614, "count": 233541, "self": 4.690532196014374, "children": { "env_step": { "total": 1969.5042953429704, "count": 233541, "self": 1533.7669706587103, "children": { "SubprocessEnvManager._take_step": { "total": 432.88985049611586, "count": 233541, "self": 15.900430910085788, "children": { "TorchPolicy.evaluate": { "total": 416.98941958603007, "count": 223055, "self": 416.98941958603007 } } }, "workers": { "total": 2.8474741881441332, "count": 233541, "self": 0.0, "children": { "worker_root": { "total": 2494.1202553820804, "count": 233541, "is_parallel": true, "self": 1249.7092998291355, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011056170000074417, "count": 1, "is_parallel": true, "self": 0.0004448969999657493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006607200000416924, "count": 2, "is_parallel": true, "self": 0.0006607200000416924 } } }, "UnityEnvironment.step": { "total": 0.040218012999957864, "count": 1, "is_parallel": true, "self": 0.00033605599981001433, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002031210000268402, "count": 1, "is_parallel": true, "self": 0.0002031210000268402 }, "communicator.exchange": { "total": 0.03895665800007464, "count": 1, "is_parallel": true, "self": 0.03895665800007464 }, "steps_from_proto": { "total": 0.0007221780000463696, "count": 1, "is_parallel": true, "self": 0.00020673100004842127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005154469999979483, "count": 2, "is_parallel": true, "self": 0.0005154469999979483 } } } } } } }, "UnityEnvironment.step": { "total": 1244.4109555529449, "count": 233540, "is_parallel": true, "self": 38.367811667073966, "children": { "UnityEnvironment._generate_step_input": { "total": 81.44528926899193, "count": 233540, "is_parallel": true, "self": 81.44528926899193 }, "communicator.exchange": { "total": 1034.0428630510055, "count": 233540, "is_parallel": true, "self": 1034.0428630510055 }, "steps_from_proto": { "total": 90.55499156587348, "count": 233540, "is_parallel": true, "self": 31.757361957884882, "children": { "_process_rank_one_or_two_observation": { "total": 58.7976296079886, "count": 467080, "is_parallel": true, "self": 58.7976296079886 } } } } } } } } } } }, "trainer_advance": { "total": 518.8933171350766, "count": 233541, "self": 7.118793377959378, "children": { "process_trajectory": { "total": 177.76065025911646, "count": 233541, "self": 176.39591615511677, "children": { "RLTrainer._checkpoint": { "total": 1.3647341039996945, "count": 10, "self": 1.3647341039996945 } } }, "_update_policy": { "total": 334.01387349800075, "count": 97, "self": 267.0242281590206, "children": { "TorchPPOOptimizer.update": { "total": 66.98964533898015, "count": 2910, "self": 66.98964533898015 } } } } } } }, "trainer_threads": { "total": 8.889996934158262e-07, "count": 1, "self": 8.889996934158262e-07 }, "TrainerController._save_models": { "total": 0.11193336899987116, "count": 1, "self": 0.0018306479996681446, "children": { "RLTrainer._checkpoint": { "total": 0.11010272100020302, "count": 1, "self": 0.11010272100020302 } } } } } } }