{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4041372537612915, "min": 1.40413498878479, "max": 1.4252727031707764, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70477.859375, "min": 67443.578125, "max": 77035.375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 111.17792792792793, "min": 101.93139293139293, "max": 435.4, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49363.0, "min": 48953.0, "max": 50275.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999963.0, "min": 49436.0, "max": 1999963.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999963.0, "min": 49436.0, "max": 1999963.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3473093509674072, "min": -0.04926830902695656, "max": 2.3473093509674072, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1042.205322265625, "min": -5.616587162017822, "max": 1089.499755859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6829647063403517, "min": 1.7630482463721644, "max": 3.892506307004446, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1635.2363296151161, "min": 200.98750008642673, "max": 1692.9491168260574, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6829647063403517, "min": 1.7630482463721644, "max": 3.892506307004446, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1635.2363296151161, "min": 200.98750008642673, "max": 1692.9491168260574, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019050138829819235, "min": 0.013711894334604343, "max": 0.019050138829819235, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03810027765963847, "min": 0.027423788669208686, "max": 0.056025167550736416, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04585328989972671, "min": 0.022759516475101313, "max": 0.05633031943192085, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.09170657979945342, "min": 0.045519032950202626, "max": 0.16696945975224176, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.433873522075005e-06, "min": 4.433873522075005e-06, "max": 0.0002953236015588, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.86774704415001e-06, "min": 8.86774704415001e-06, "max": 0.0008439726186758001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10147792500000001, "min": 0.10147792500000001, "max": 0.1984412, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20295585000000002, "min": 0.20295585000000002, "max": 0.5813241999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.374845750000012e-05, "min": 8.374845750000012e-05, "max": 0.0049222158800000014, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016749691500000024, "min": 0.00016749691500000024, "max": 0.014068077580000001, "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": "1678922760", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678925212" }, "total": 2451.780229306, "count": 1, "self": 0.3885880980001275, "children": { "run_training.setup": { "total": 0.1188868510000134, "count": 1, "self": 0.1188868510000134 }, "TrainerController.start_learning": { "total": 2451.272754357, "count": 1, "self": 4.46860673304127, "children": { "TrainerController._reset_env": { "total": 9.192531967000008, "count": 1, "self": 9.192531967000008 }, "TrainerController.advance": { "total": 2437.491365653959, "count": 230913, "self": 4.83964995702263, "children": { "env_step": { "total": 1906.4031166359316, "count": 230913, "self": 1607.8986496128823, "children": { "SubprocessEnvManager._take_step": { "total": 295.44157585206597, "count": 230913, "self": 17.45589276903604, "children": { "TorchPolicy.evaluate": { "total": 277.9856830830299, "count": 222897, "self": 277.9856830830299 } } }, "workers": { "total": 3.062891170983278, "count": 230913, "self": 0.0, "children": { "worker_root": { "total": 2442.957639986973, "count": 230913, "is_parallel": true, "self": 1134.0454963640118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009934320000013486, "count": 1, "is_parallel": true, "self": 0.0002621779999856244, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007312540000157242, "count": 2, "is_parallel": true, "self": 0.0007312540000157242 } } }, "UnityEnvironment.step": { "total": 0.0696399999999926, "count": 1, "is_parallel": true, "self": 0.00034410299997489346, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003803600000082952, "count": 1, "is_parallel": true, "self": 0.0003803600000082952 }, "communicator.exchange": { "total": 0.06819756900000584, "count": 1, "is_parallel": true, "self": 0.06819756900000584 }, "steps_from_proto": { "total": 0.000717968000003566, "count": 1, "is_parallel": true, "self": 0.00019705100001488063, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005209169999886853, "count": 2, "is_parallel": true, "self": 0.0005209169999886853 } } } } } } }, "UnityEnvironment.step": { "total": 1308.9121436229611, "count": 230912, "is_parallel": true, "self": 39.63001980686863, "children": { "UnityEnvironment._generate_step_input": { "total": 79.12516590996461, "count": 230912, "is_parallel": true, "self": 79.12516590996461 }, "communicator.exchange": { "total": 1098.9656550750578, "count": 230912, "is_parallel": true, "self": 1098.9656550750578 }, "steps_from_proto": { "total": 91.19130283107015, "count": 230912, "is_parallel": true, "self": 33.718578399068036, "children": { "_process_rank_one_or_two_observation": { "total": 57.47272443200211, "count": 461824, "is_parallel": true, "self": 57.47272443200211 } } } } } } } } } } }, "trainer_advance": { "total": 526.2485990610045, "count": 230913, "self": 7.2637495620875825, "children": { "process_trajectory": { "total": 142.26541541891643, "count": 230913, "self": 140.9992591899165, "children": { "RLTrainer._checkpoint": { "total": 1.2661562289999324, "count": 10, "self": 1.2661562289999324 } } }, "_update_policy": { "total": 376.71943408000044, "count": 96, "self": 316.97932662200117, "children": { "TorchPPOOptimizer.update": { "total": 59.74010745799927, "count": 2880, "self": 59.74010745799927 } } } } } } }, "trainer_threads": { "total": 1.247000000148546e-06, "count": 1, "self": 1.247000000148546e-06 }, "TrainerController._save_models": { "total": 0.12024875599990992, "count": 1, "self": 0.002235479999853851, "children": { "RLTrainer._checkpoint": { "total": 0.11801327600005607, "count": 1, "self": 0.11801327600005607 } } } } } } }