{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.405004620552063, "min": 1.405004620552063, "max": 1.4307875633239746, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68873.328125, "min": 68540.640625, "max": 78329.28125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 137.88055555555556, "min": 111.60585585585585, "max": 398.1666666666667, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49637.0, "min": 48917.0, "max": 50495.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999943.0, "min": 49919.0, "max": 1999943.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999943.0, "min": 49919.0, "max": 1999943.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.187992811203003, "min": 0.20747637748718262, "max": 2.332099437713623, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 787.6774291992188, "min": 25.934547424316406, "max": 994.457275390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.303026090727912, "min": 1.7428654181957244, "max": 3.65738783291606, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1189.0893926620483, "min": 217.85817727446556, "max": 1543.4939528107643, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.303026090727912, "min": 1.7428654181957244, "max": 3.65738783291606, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1189.0893926620483, "min": 217.85817727446556, "max": 1543.4939528107643, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01615269749502962, "min": 0.013981970222569848, "max": 0.020050739263671048, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03230539499005924, "min": 0.027963940445139696, "max": 0.060152217791013145, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.045633764564991, "min": 0.01899592811241746, "max": 0.06344751759121815, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.091267529129982, "min": 0.03863510359078646, "max": 0.18422923609614372, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7952487349500017e-06, "min": 3.7952487349500017e-06, "max": 0.0002952995265668249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 7.5904974699000035e-06, "min": 7.5904974699000035e-06, "max": 0.0008441637186120999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126505000000002, "min": 0.10126505000000002, "max": 0.19843317500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20253010000000005, "min": 0.20253010000000005, "max": 0.5813878999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.312599500000005e-05, "min": 7.312599500000005e-05, "max": 0.0049218154325, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001462519900000001, "min": 0.0001462519900000001, "max": 0.014071256209999997, "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": "1689147046", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1689149425" }, "total": 2378.7228424760006, "count": 1, "self": 0.4328665790008017, "children": { "run_training.setup": { "total": 0.048326076999728684, "count": 1, "self": 0.048326076999728684 }, "TrainerController.start_learning": { "total": 2378.24164982, "count": 1, "self": 4.058937440804584, "children": { "TrainerController._reset_env": { "total": 4.703298620999703, "count": 1, "self": 4.703298620999703 }, "TrainerController.advance": { "total": 2369.3613660591955, "count": 230130, "self": 4.308666537195677, "children": { "env_step": { "total": 1844.213967775997, "count": 230130, "self": 1552.2512323841702, "children": { "SubprocessEnvManager._take_step": { "total": 289.24571482869305, "count": 230130, "self": 16.938327991299047, "children": { "TorchPolicy.evaluate": { "total": 272.307386837394, "count": 222936, "self": 272.307386837394 } } }, "workers": { "total": 2.717020563133701, "count": 230130, "self": 0.0, "children": { "worker_root": { "total": 2370.707730090513, "count": 230130, "is_parallel": true, "self": 1102.7658935763948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008697729999767034, "count": 1, "is_parallel": true, "self": 0.0002408620002825046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006289109996941988, "count": 2, "is_parallel": true, "self": 0.0006289109996941988 } } }, "UnityEnvironment.step": { "total": 0.04888089099949866, "count": 1, "is_parallel": true, "self": 0.0003413579988773563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021116200059623225, "count": 1, "is_parallel": true, "self": 0.00021116200059623225 }, "communicator.exchange": { "total": 0.047584046000338276, "count": 1, "is_parallel": true, "self": 0.047584046000338276 }, "steps_from_proto": { "total": 0.0007443249996867962, "count": 1, "is_parallel": true, "self": 0.00020577899977070047, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005385459999160958, "count": 2, "is_parallel": true, "self": 0.0005385459999160958 } } } } } } }, "UnityEnvironment.step": { "total": 1267.9418365141182, "count": 230129, "is_parallel": true, "self": 39.15356750670526, "children": { "UnityEnvironment._generate_step_input": { "total": 80.8273006669624, "count": 230129, "is_parallel": true, "self": 80.8273006669624 }, "communicator.exchange": { "total": 1051.8372768571044, "count": 230129, "is_parallel": true, "self": 1051.8372768571044 }, "steps_from_proto": { "total": 96.12369148334619, "count": 230129, "is_parallel": true, "self": 34.142865517596874, "children": { "_process_rank_one_or_two_observation": { "total": 61.98082596574932, "count": 460258, "is_parallel": true, "self": 61.98082596574932 } } } } } } } } } } }, "trainer_advance": { "total": 520.8387317460028, "count": 230130, "self": 6.442261750969919, "children": { "process_trajectory": { "total": 125.54322337403391, "count": 230130, "self": 124.18924591903578, "children": { "RLTrainer._checkpoint": { "total": 1.3539774549981303, "count": 10, "self": 1.3539774549981303 } } }, "_update_policy": { "total": 388.853246620999, "count": 96, "self": 328.87994762397466, "children": { "TorchPPOOptimizer.update": { "total": 59.97329899702436, "count": 2880, "self": 59.97329899702436 } } } } } } }, "trainer_threads": { "total": 9.559998943586834e-07, "count": 1, "self": 9.559998943586834e-07 }, "TrainerController._save_models": { "total": 0.11804674300037732, "count": 1, "self": 0.002521102000173414, "children": { "RLTrainer._checkpoint": { "total": 0.1155256410002039, "count": 1, "self": 0.1155256410002039 } } } } } } }