{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4064801931381226, "min": 1.4064801931381226, "max": 1.4279911518096924, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69447.7734375, "min": 68317.3828125, "max": 77528.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.83644859813084, "min": 76.83644859813084, "max": 385.2846153846154, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49329.0, "min": 49132.0, "max": 50087.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999961.0, "min": 49568.0, "max": 1999961.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999961.0, "min": 49568.0, "max": 1999961.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.445634126663208, "min": 0.12965139746665955, "max": 2.5088255405426025, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1570.09716796875, "min": 16.72503089904785, "max": 1570.8626708984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.797586200486091, "min": 1.8003241507581962, "max": 4.020896989797496, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2438.0503407120705, "min": 232.2418154478073, "max": 2464.809854745865, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.797586200486091, "min": 1.8003241507581962, "max": 4.020896989797496, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2438.0503407120705, "min": 232.2418154478073, "max": 2464.809854745865, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015310336204129272, "min": 0.01449860742852454, "max": 0.020427801795691872, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045931008612387816, "min": 0.029081542846688534, "max": 0.05682855889220567, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06596285754607784, "min": 0.0210447051251928, "max": 0.06596285754607784, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1978885726382335, "min": 0.0420894102503856, "max": 0.1978885726382335, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6799987733666573e-06, "min": 3.6799987733666573e-06, "max": 0.000295355026548325, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1039996320099971e-05, "min": 1.1039996320099971e-05, "max": 0.0008444043185318998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122663333333337, "min": 0.10122663333333337, "max": 0.19845167499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036799000000001, "min": 0.20758825000000003, "max": 0.5814680999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.12090033333332e-05, "min": 7.12090033333332e-05, "max": 0.0049227385825, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021362700999999961, "min": 0.00021362700999999961, "max": 0.014075258189999999, "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": "1709037557", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709040097" }, "total": 2540.142873102, "count": 1, "self": 0.43960348500013424, "children": { "run_training.setup": { "total": 0.08941479199995683, "count": 1, "self": 0.08941479199995683 }, "TrainerController.start_learning": { "total": 2539.613854825, "count": 1, "self": 4.695020804022988, "children": { "TrainerController._reset_env": { "total": 3.188099371000021, "count": 1, "self": 3.188099371000021 }, "TrainerController.advance": { "total": 2531.604486687977, "count": 232037, "self": 5.118258105914265, "children": { "env_step": { "total": 2039.9452501160602, "count": 232037, "self": 1686.7940530621177, "children": { "SubprocessEnvManager._take_step": { "total": 350.0136250150024, "count": 232037, "self": 19.20530185401867, "children": { "TorchPolicy.evaluate": { "total": 330.8083231609837, "count": 222872, "self": 330.8083231609837 } } }, "workers": { "total": 3.1375720389401067, "count": 232037, "self": 0.0, "children": { "worker_root": { "total": 2531.7689632129022, "count": 232037, "is_parallel": true, "self": 1165.154466053963, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010401069999943502, "count": 1, "is_parallel": true, "self": 0.00028864799992334156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007514590000710086, "count": 2, "is_parallel": true, "self": 0.0007514590000710086 } } }, "UnityEnvironment.step": { "total": 0.03148949100000209, "count": 1, "is_parallel": true, "self": 0.00037243800034048036, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002070839998395968, "count": 1, "is_parallel": true, "self": 0.0002070839998395968 }, "communicator.exchange": { "total": 0.030016374999831896, "count": 1, "is_parallel": true, "self": 0.030016374999831896 }, "steps_from_proto": { "total": 0.0008935939999901166, "count": 1, "is_parallel": true, "self": 0.0002560430000357883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006375509999543283, "count": 2, "is_parallel": true, "self": 0.0006375509999543283 } } } } } } }, "UnityEnvironment.step": { "total": 1366.6144971589392, "count": 232036, "is_parallel": true, "self": 43.02813611570241, "children": { "UnityEnvironment._generate_step_input": { "total": 92.24108244315903, "count": 232036, "is_parallel": true, "self": 92.24108244315903 }, "communicator.exchange": { "total": 1133.5399512910099, "count": 232036, "is_parallel": true, "self": 1133.5399512910099 }, "steps_from_proto": { "total": 97.80532730906793, "count": 232036, "is_parallel": true, "self": 36.93729079305945, "children": { "_process_rank_one_or_two_observation": { "total": 60.86803651600849, "count": 464072, "is_parallel": true, "self": 60.86803651600849 } } } } } } } } } } }, "trainer_advance": { "total": 486.54097846600234, "count": 232037, "self": 7.227233451166512, "children": { "process_trajectory": { "total": 163.54904656583608, "count": 232037, "self": 162.11522267183636, "children": { "RLTrainer._checkpoint": { "total": 1.4338238939997154, "count": 10, "self": 1.4338238939997154 } } }, "_update_policy": { "total": 315.76469844899975, "count": 97, "self": 253.52094966899745, "children": { "TorchPPOOptimizer.update": { "total": 62.243748780002306, "count": 2910, "self": 62.243748780002306 } } } } } } }, "trainer_threads": { "total": 1.0660000953066628e-06, "count": 1, "self": 1.0660000953066628e-06 }, "TrainerController._save_models": { "total": 0.12624689599988415, "count": 1, "self": 0.0019915919997401943, "children": { "RLTrainer._checkpoint": { "total": 0.12425530400014395, "count": 1, "self": 0.12425530400014395 } } } } } } }