{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4012024402618408, "min": 1.4012024402618408, "max": 1.4291012287139893, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71321.203125, "min": 68345.1484375, "max": 78807.9921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.39642857142857, "min": 77.48584905660377, "max": 391.14728682170545, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48942.0, "min": 48857.0, "max": 50458.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999931.0, "min": 49976.0, "max": 1999931.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999931.0, "min": 49976.0, "max": 1999931.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4002132415771484, "min": 0.11803723871707916, "max": 2.480893850326538, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1344.119384765625, "min": 15.108766555786133, "max": 1541.226806640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7597381950489113, "min": 1.616500847041607, "max": 4.021805042387746, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2105.4533892273903, "min": 206.91210842132568, "max": 2455.576726913452, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7597381950489113, "min": 1.616500847041607, "max": 4.021805042387746, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2105.4533892273903, "min": 206.91210842132568, "max": 2455.576726913452, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017315627220563734, "min": 0.013567450927409179, "max": 0.020938270801949935, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0519468816616912, "min": 0.027134901854818358, "max": 0.05733096066687721, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051048095317350495, "min": 0.021771134746571382, "max": 0.06597702416280905, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15314428595205148, "min": 0.043542269493142764, "max": 0.19019070404271285, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4020988660000046e-06, "min": 3.4020988660000046e-06, "max": 0.00029537490154169996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0206296598000014e-05, "min": 1.0206296598000014e-05, "max": 0.00084440926853025, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113400000000002, "min": 0.10113400000000002, "max": 0.1984583000000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30340200000000006, "min": 0.20743290000000003, "max": 0.5814697500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.658660000000009e-05, "min": 6.658660000000009e-05, "max": 0.00492306917, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019975980000000026, "min": 0.00019975980000000026, "max": 0.014075340524999999, "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": "1699611438", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1699613818" }, "total": 2380.57875327, "count": 1, "self": 0.42423461799990037, "children": { "run_training.setup": { "total": 0.042484397000066565, "count": 1, "self": 0.042484397000066565 }, "TrainerController.start_learning": { "total": 2380.1120342550003, "count": 1, "self": 4.387640111970541, "children": { "TrainerController._reset_env": { "total": 8.916189699000029, "count": 1, "self": 8.916189699000029 }, "TrainerController.advance": { "total": 2366.7026234560294, "count": 232535, "self": 4.773335477848832, "children": { "env_step": { "total": 1871.443371358128, "count": 232535, "self": 1542.569578529091, "children": { "SubprocessEnvManager._take_step": { "total": 326.07487009901286, "count": 232535, "self": 16.283396907898577, "children": { "TorchPolicy.evaluate": { "total": 309.7914731911143, "count": 223036, "self": 309.7914731911143 } } }, "workers": { "total": 2.79892273002406, "count": 232535, "self": 0.0, "children": { "worker_root": { "total": 2372.6297841600363, "count": 232535, "is_parallel": true, "self": 1114.795638280046, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007875019999801225, "count": 1, "is_parallel": true, "self": 0.0002011889999948835, "children": { "_process_rank_one_or_two_observation": { "total": 0.000586312999985239, "count": 2, "is_parallel": true, "self": 0.000586312999985239 } } }, "UnityEnvironment.step": { "total": 0.028147166000053403, "count": 1, "is_parallel": true, "self": 0.00028524400011065154, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020413499998994666, "count": 1, "is_parallel": true, "self": 0.00020413499998994666 }, "communicator.exchange": { "total": 0.027016914000000725, "count": 1, "is_parallel": true, "self": 0.027016914000000725 }, "steps_from_proto": { "total": 0.0006408729999520801, "count": 1, "is_parallel": true, "self": 0.00018307800007733022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004577949998747499, "count": 2, "is_parallel": true, "self": 0.0004577949998747499 } } } } } } }, "UnityEnvironment.step": { "total": 1257.8341458799903, "count": 232534, "is_parallel": true, "self": 39.498838281968574, "children": { "UnityEnvironment._generate_step_input": { "total": 81.09543939206662, "count": 232534, "is_parallel": true, "self": 81.09543939206662 }, "communicator.exchange": { "total": 1049.1289494049688, "count": 232534, "is_parallel": true, "self": 1049.1289494049688 }, "steps_from_proto": { "total": 88.1109188009865, "count": 232534, "is_parallel": true, "self": 30.780874826234253, "children": { "_process_rank_one_or_two_observation": { "total": 57.33004397475224, "count": 465068, "is_parallel": true, "self": 57.33004397475224 } } } } } } } } } } }, "trainer_advance": { "total": 490.48591662005276, "count": 232535, "self": 6.5035649830672355, "children": { "process_trajectory": { "total": 150.44238174498673, "count": 232535, "self": 149.39410237698712, "children": { "RLTrainer._checkpoint": { "total": 1.048279367999612, "count": 10, "self": 1.048279367999612 } } }, "_update_policy": { "total": 333.5399698919988, "count": 97, "self": 271.57929867999553, "children": { "TorchPPOOptimizer.update": { "total": 61.96067121200326, "count": 2910, "self": 61.96067121200326 } } } } } } }, "trainer_threads": { "total": 1.3820003914588597e-06, "count": 1, "self": 1.3820003914588597e-06 }, "TrainerController._save_models": { "total": 0.10557960599999205, "count": 1, "self": 0.0018851429999813263, "children": { "RLTrainer._checkpoint": { "total": 0.10369446300001073, "count": 1, "self": 0.10369446300001073 } } } } } } }