{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4062309265136719, "min": 1.4062309265136719, "max": 1.4278923273086548, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69294.84375, "min": 67979.109375, "max": 79551.921875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.02083333333333, "min": 89.49364791288566, "max": 401.768, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49450.0, "min": 48879.0, "max": 50221.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49911.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49911.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.438527822494507, "min": 0.09780031442642212, "max": 2.438527822494507, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1170.493408203125, "min": 12.127239227294922, "max": 1332.8892822265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7280306022614242, "min": 1.8237538308866563, "max": 3.9569639065775317, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1789.4546890854836, "min": 226.14547502994537, "max": 2184.2440764307976, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7280306022614242, "min": 1.8237538308866563, "max": 3.9569639065775317, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1789.4546890854836, "min": 226.14547502994537, "max": 2184.2440764307976, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017361233864923834, "min": 0.014248796653798005, "max": 0.021369693145970814, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052083701594771506, "min": 0.028683633828768505, "max": 0.0611283443402499, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04952215018371741, "min": 0.0223643203265965, "max": 0.061948266004522634, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14856645055115222, "min": 0.044728640653193, "max": 0.1858447980135679, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1972989342666655e-06, "min": 3.1972989342666655e-06, "max": 0.00029530492656502493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.591896802799997e-06, "min": 9.591896802799997e-06, "max": 0.0008438917687027498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106573333333334, "min": 0.10106573333333334, "max": 0.198434975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031972, "min": 0.20727630000000008, "max": 0.5812972499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.318009333333336e-05, "min": 6.318009333333336e-05, "max": 0.004921905252500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018954028000000008, "min": 0.00018954028000000008, "max": 0.014066732775, "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": "1670348831", "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \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": "1670351233" }, "total": 2402.166885006, "count": 1, "self": 0.39442775199995594, "children": { "run_training.setup": { "total": 0.11512527299998965, "count": 1, "self": 0.11512527299998965 }, "TrainerController.start_learning": { "total": 2401.657331981, "count": 1, "self": 4.089023923057539, "children": { "TrainerController._reset_env": { "total": 10.738572454000177, "count": 1, "self": 10.738572454000177 }, "TrainerController.advance": { "total": 2386.7048975909424, "count": 231554, "self": 4.424321428166877, "children": { "env_step": { "total": 1887.6360909168793, "count": 231554, "self": 1586.9535943789213, "children": { "SubprocessEnvManager._take_step": { "total": 298.01193019797256, "count": 231554, "self": 15.291472545786519, "children": { "TorchPolicy.evaluate": { "total": 282.72045765218604, "count": 222967, "self": 70.86195514819656, "children": { "TorchPolicy.sample_actions": { "total": 211.85850250398948, "count": 222967, "self": 211.85850250398948 } } } } }, "workers": { "total": 2.6705663399854984, "count": 231554, "self": 0.0, "children": { "worker_root": { "total": 2393.1847686320216, "count": 231554, "is_parallel": true, "self": 1083.1399719319213, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001977944999907777, "count": 1, "is_parallel": true, "self": 0.0003292229998805851, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016487220000271918, "count": 2, "is_parallel": true, "self": 0.0016487220000271918 } } }, "UnityEnvironment.step": { "total": 0.029257251999979417, "count": 1, "is_parallel": true, "self": 0.000298952000321151, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000190470000006826, "count": 1, "is_parallel": true, "self": 0.000190470000006826 }, "communicator.exchange": { "total": 0.027963252999825272, "count": 1, "is_parallel": true, "self": 0.027963252999825272 }, "steps_from_proto": { "total": 0.0008045769998261676, "count": 1, "is_parallel": true, "self": 0.0002688159997887851, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005357610000373825, "count": 2, "is_parallel": true, "self": 0.0005357610000373825 } } } } } } }, "UnityEnvironment.step": { "total": 1310.0447967001003, "count": 231553, "is_parallel": true, "self": 37.7240385671837, "children": { "UnityEnvironment._generate_step_input": { "total": 81.66304179398844, "count": 231553, "is_parallel": true, "self": 81.66304179398844 }, "communicator.exchange": { "total": 1090.7786184829909, "count": 231553, "is_parallel": true, "self": 1090.7786184829909 }, "steps_from_proto": { "total": 99.87909785593729, "count": 231553, "is_parallel": true, "self": 41.23633534999021, "children": { "_process_rank_one_or_two_observation": { "total": 58.642762505947076, "count": 463106, "is_parallel": true, "self": 58.642762505947076 } } } } } } } } } } }, "trainer_advance": { "total": 494.64448524589625, "count": 231554, "self": 6.858601793954676, "children": { "process_trajectory": { "total": 157.75348070794166, "count": 231554, "self": 157.23532499394173, "children": { "RLTrainer._checkpoint": { "total": 0.5181557139999313, "count": 4, "self": 0.5181557139999313 } } }, "_update_policy": { "total": 330.0324027439999, "count": 97, "self": 274.0544825959985, "children": { "TorchPPOOptimizer.update": { "total": 55.97792014800143, "count": 2910, "self": 55.97792014800143 } } } } } } }, "trainer_threads": { "total": 1.029999566526385e-06, "count": 1, "self": 1.029999566526385e-06 }, "TrainerController._save_models": { "total": 0.12483698300002288, "count": 1, "self": 0.0021740319998571067, "children": { "RLTrainer._checkpoint": { "total": 0.12266295100016578, "count": 1, "self": 0.12266295100016578 } } } } } } }