{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4059253931045532, "min": 1.4059253931045532, "max": 1.4275312423706055, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69338.8359375, "min": 67480.203125, "max": 78967.1640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.67603305785124, "min": 79.36977491961414, "max": 422.0504201680672, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49414.0, "min": 49287.0, "max": 50224.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49928.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49928.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.499358892440796, "min": -0.07402683794498444, "max": 2.5001392364501953, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1512.1121826171875, "min": -8.735166549682617, "max": 1545.660888671875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.965329560662104, "min": 1.767062255386579, "max": 3.9977468198963573, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2399.024384200573, "min": 208.5133461356163, "max": 2456.6529887914658, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.965329560662104, "min": 1.767062255386579, "max": 3.9977468198963573, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2399.024384200573, "min": 208.5133461356163, "max": 2456.6529887914658, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018598945477020203, "min": 0.012923321737131725, "max": 0.02103996479159428, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.055796836431060606, "min": 0.02584664347426345, "max": 0.06311989437478284, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05995257053938177, "min": 0.023072836672266325, "max": 0.06097219015161196, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17985771161814532, "min": 0.04614567334453265, "max": 0.1829165704548359, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3463988845666795e-06, "min": 3.3463988845666795e-06, "max": 0.00029535667654777503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0039196653700038e-05, "min": 1.0039196653700038e-05, "max": 0.0008439922686692499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111543333333335, "min": 0.10111543333333335, "max": 0.19845222500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30334630000000007, "min": 0.20743315, "max": 0.5813307500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.566012333333354e-05, "min": 6.566012333333354e-05, "max": 0.004922766027500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019698037000000064, "min": 0.00019698037000000064, "max": 0.014068404425, "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": "1671588779", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1.21.6", "end_time_seconds": "1671591213" }, "total": 2434.155237786, "count": 1, "self": 0.442129819999991, "children": { "run_training.setup": { "total": 0.10757017399998858, "count": 1, "self": 0.10757017399998858 }, "TrainerController.start_learning": { "total": 2433.6055377919997, "count": 1, "self": 4.5625349870474565, "children": { "TrainerController._reset_env": { "total": 8.171639657000014, "count": 1, "self": 8.171639657000014 }, "TrainerController.advance": { "total": 2420.7439709039522, "count": 232317, "self": 4.705772519945185, "children": { "env_step": { "total": 1925.7646820150132, "count": 232317, "self": 1620.4214420510518, "children": { "SubprocessEnvManager._take_step": { "total": 302.2858712670014, "count": 232317, "self": 15.875445235026461, "children": { "TorchPolicy.evaluate": { "total": 286.41042603197496, "count": 222862, "self": 72.40134131186818, "children": { "TorchPolicy.sample_actions": { "total": 214.00908472010678, "count": 222862, "self": 214.00908472010678 } } } } }, "workers": { "total": 3.0573686969599976, "count": 232317, "self": 0.0, "children": { "worker_root": { "total": 2424.591529738945, "count": 232317, "is_parallel": true, "self": 1094.7910408250302, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022819929999968736, "count": 1, "is_parallel": true, "self": 0.00031930300002613876, "children": { "_process_rank_one_or_two_observation": { "total": 0.001962689999970735, "count": 2, "is_parallel": true, "self": 0.001962689999970735 } } }, "UnityEnvironment.step": { "total": 0.0352473259999897, "count": 1, "is_parallel": true, "self": 0.00030229099996859077, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019956300002377247, "count": 1, "is_parallel": true, "self": 0.00019956300002377247 }, "communicator.exchange": { "total": 0.03400807700000996, "count": 1, "is_parallel": true, "self": 0.03400807700000996 }, "steps_from_proto": { "total": 0.000737394999987373, "count": 1, "is_parallel": true, "self": 0.00026107000002184577, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047632499996552724, "count": 2, "is_parallel": true, "self": 0.00047632499996552724 } } } } } } }, "UnityEnvironment.step": { "total": 1329.800488913915, "count": 232316, "is_parallel": true, "self": 38.22829252399811, "children": { "UnityEnvironment._generate_step_input": { "total": 78.67093673900138, "count": 232316, "is_parallel": true, "self": 78.67093673900138 }, "communicator.exchange": { "total": 1111.3996779868996, "count": 232316, "is_parallel": true, "self": 1111.3996779868996 }, "steps_from_proto": { "total": 101.50158166401582, "count": 232316, "is_parallel": true, "self": 41.080452915856824, "children": { "_process_rank_one_or_two_observation": { "total": 60.42112874815899, "count": 464632, "is_parallel": true, "self": 60.42112874815899 } } } } } } } } } } }, "trainer_advance": { "total": 490.273516368994, "count": 232317, "self": 7.2316051079600925, "children": { "process_trajectory": { "total": 161.11654374403378, "count": 232317, "self": 159.8704258480338, "children": { "RLTrainer._checkpoint": { "total": 1.246117895999987, "count": 10, "self": 1.246117895999987 } } }, "_update_policy": { "total": 321.92536751700015, "count": 97, "self": 266.90224942399976, "children": { "TorchPPOOptimizer.update": { "total": 55.02311809300039, "count": 2910, "self": 55.02311809300039 } } } } } } }, "trainer_threads": { "total": 1.097000222216593e-06, "count": 1, "self": 1.097000222216593e-06 }, "TrainerController._save_models": { "total": 0.12739114699979837, "count": 1, "self": 0.002033143999597087, "children": { "RLTrainer._checkpoint": { "total": 0.12535800300020128, "count": 1, "self": 0.12535800300020128 } } } } } } }