{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3999911546707153, "min": 1.3999911546707153, "max": 1.4254693984985352, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70832.5546875, "min": 68701.953125, "max": 77428.03125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 68.01936376210236, "min": 66.20295698924731, "max": 411.24590163934425, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49178.0, "min": 49178.0, "max": 50172.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999961.0, "min": 49983.0, "max": 1999961.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999961.0, "min": 49983.0, "max": 1999961.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5342283248901367, "min": 0.055319979786872864, "max": 2.5440847873687744, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1832.2470703125, "min": 6.6937174797058105, "max": 1836.94775390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9295000326748872, "min": 1.7680493077217054, "max": 4.044752422152132, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2841.0285236239433, "min": 213.93396623432636, "max": 2865.4711268544197, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9295000326748872, "min": 1.7680493077217054, "max": 4.044752422152132, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2841.0285236239433, "min": 213.93396623432636, "max": 2865.4711268544197, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01686525253866825, "min": 0.013672868999795659, "max": 0.02083468255586922, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05059575761600475, "min": 0.027345737999591318, "max": 0.05869958514231257, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.061821760899490784, "min": 0.023014491299788158, "max": 0.07025906164199114, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18546528269847234, "min": 0.046028982599576315, "max": 0.18746341144045192, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.859348713583336e-06, "min": 3.859348713583336e-06, "max": 0.000295362976545675, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1578046140750009e-05, "min": 1.1578046140750009e-05, "max": 0.00084402286865905, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128641666666667, "min": 0.10128641666666667, "max": 0.19845432500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30385925, "min": 0.20770125, "max": 0.58134095, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.419219166666672e-05, "min": 7.419219166666672e-05, "max": 0.004922870817499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022257657500000016, "min": 0.00022257657500000016, "max": 0.014068913405000001, "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": "1671091054", "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": "1671093194" }, "total": 2140.3331431879997, "count": 1, "self": 0.39033066399952077, "children": { "run_training.setup": { "total": 0.11495345000002999, "count": 1, "self": 0.11495345000002999 }, "TrainerController.start_learning": { "total": 2139.827859074, "count": 1, "self": 3.717056053977103, "children": { "TrainerController._reset_env": { "total": 10.030463542999996, "count": 1, "self": 10.030463542999996 }, "TrainerController.advance": { "total": 2125.967298165023, "count": 233930, "self": 3.7981505729785567, "children": { "env_step": { "total": 1665.5754644479446, "count": 233930, "self": 1400.0357212478616, "children": { "SubprocessEnvManager._take_step": { "total": 263.0007545870594, "count": 233930, "self": 14.140335303931806, "children": { "TorchPolicy.evaluate": { "total": 248.8604192831276, "count": 222967, "self": 62.98576209732482, "children": { "TorchPolicy.sample_actions": { "total": 185.8746571858028, "count": 222967, "self": 185.8746571858028 } } } } }, "workers": { "total": 2.538988613023548, "count": 233930, "self": 0.0, "children": { "worker_root": { "total": 2132.433781765019, "count": 233930, "is_parallel": true, "self": 980.3343539520531, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024006180001379107, "count": 1, "is_parallel": true, "self": 0.0004253340000559547, "children": { "_process_rank_one_or_two_observation": { "total": 0.001975284000081956, "count": 2, "is_parallel": true, "self": 0.001975284000081956 } } }, "UnityEnvironment.step": { "total": 0.026880347000087568, "count": 1, "is_parallel": true, "self": 0.0002782000003662688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021868699991500762, "count": 1, "is_parallel": true, "self": 0.00021868699991500762 }, "communicator.exchange": { "total": 0.025694968999914636, "count": 1, "is_parallel": true, "self": 0.025694968999914636 }, "steps_from_proto": { "total": 0.0006884909998916555, "count": 1, "is_parallel": true, "self": 0.000234519999821714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004539710000699415, "count": 2, "is_parallel": true, "self": 0.0004539710000699415 } } } } } } }, "UnityEnvironment.step": { "total": 1152.0994278129658, "count": 233929, "is_parallel": true, "self": 33.634095385099045, "children": { "UnityEnvironment._generate_step_input": { "total": 75.61055896392463, "count": 233929, "is_parallel": true, "self": 75.61055896392463 }, "communicator.exchange": { "total": 951.6960263040248, "count": 233929, "is_parallel": true, "self": 951.6960263040248 }, "steps_from_proto": { "total": 91.15874715991731, "count": 233929, "is_parallel": true, "self": 37.42035431196177, "children": { "_process_rank_one_or_two_observation": { "total": 53.73839284795554, "count": 467858, "is_parallel": true, "self": 53.73839284795554 } } } } } } } } } } }, "trainer_advance": { "total": 456.5936831440995, "count": 233930, "self": 5.657198053096863, "children": { "process_trajectory": { "total": 146.46940265800094, "count": 233930, "self": 146.0141291470013, "children": { "RLTrainer._checkpoint": { "total": 0.455273510999632, "count": 4, "self": 0.455273510999632 } } }, "_update_policy": { "total": 304.4670824330017, "count": 97, "self": 252.17035869798474, "children": { "TorchPPOOptimizer.update": { "total": 52.29672373501694, "count": 2910, "self": 52.29672373501694 } } } } } } }, "trainer_threads": { "total": 8.729998626222368e-07, "count": 1, "self": 8.729998626222368e-07 }, "TrainerController._save_models": { "total": 0.11304043900008764, "count": 1, "self": 0.002006434000122681, "children": { "RLTrainer._checkpoint": { "total": 0.11103400499996496, "count": 1, "self": 0.11103400499996496 } } } } } } }