ppo-Huggy / run_logs /timers.json
diegocp01's picture
Huggy
e89f4bf verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4048776626586914,
"min": 1.4048776626586914,
"max": 1.4284061193466187,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70229.8359375,
"min": 69170.6953125,
"max": 76587.796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.17931034482758,
"min": 78.55325914149444,
"max": 380.68702290076334,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49404.0,
"min": 49043.0,
"max": 50011.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49707.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49707.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.494422674179077,
"min": 0.07317859679460526,
"max": 2.5017759799957275,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1446.76513671875,
"min": 9.51321792602539,
"max": 1533.252197265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8809091055187688,
"min": 1.8256965664716867,
"max": 3.9653776095547806,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2250.927281200886,
"min": 237.34055364131927,
"max": 2342.4499749541283,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8809091055187688,
"min": 1.8256965664716867,
"max": 3.9653776095547806,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2250.927281200886,
"min": 237.34055364131927,
"max": 2342.4499749541283,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0164978930222181,
"min": 0.013008734745380935,
"max": 0.01970468692064363,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04949367906665429,
"min": 0.02601746949076187,
"max": 0.056547241054552916,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054846841510799195,
"min": 0.023000867354373136,
"max": 0.060657115963598095,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1645405245323976,
"min": 0.04600173470874627,
"max": 0.17551895988484226,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.708498763866666e-06,
"min": 3.708498763866666e-06,
"max": 0.00029532075155975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1125496291599997e-05,
"min": 1.1125496291599997e-05,
"max": 0.0008440774686408498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123613333333335,
"min": 0.10123613333333335,
"max": 0.19844024999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30370840000000004,
"min": 0.20760920000000005,
"max": 0.5813591500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.168305333333335e-05,
"min": 7.168305333333335e-05,
"max": 0.0049221684750000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021504916000000005,
"min": 0.00021504916000000005,
"max": 0.014069821585,
"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": "1727134031",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727136409"
},
"total": 2378.1489223259996,
"count": 1,
"self": 0.4275559729994711,
"children": {
"run_training.setup": {
"total": 0.05363857099996494,
"count": 1,
"self": 0.05363857099996494
},
"TrainerController.start_learning": {
"total": 2377.667727782,
"count": 1,
"self": 4.445904427073856,
"children": {
"TrainerController._reset_env": {
"total": 2.5104832790000273,
"count": 1,
"self": 2.5104832790000273
},
"TrainerController.advance": {
"total": 2370.5913380439265,
"count": 232781,
"self": 4.405718601137323,
"children": {
"env_step": {
"total": 1873.9016285458904,
"count": 232781,
"self": 1480.1501234579912,
"children": {
"SubprocessEnvManager._take_step": {
"total": 391.04851847801274,
"count": 232781,
"self": 15.503613629894517,
"children": {
"TorchPolicy.evaluate": {
"total": 375.5449048481182,
"count": 222938,
"self": 375.5449048481182
}
}
},
"workers": {
"total": 2.702986609886466,
"count": 232781,
"self": 0.0,
"children": {
"worker_root": {
"total": 2370.3716304679433,
"count": 232781,
"is_parallel": true,
"self": 1173.4487260820993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007468619999144721,
"count": 1,
"is_parallel": true,
"self": 0.00020392700002958009,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000542934999884892,
"count": 2,
"is_parallel": true,
"self": 0.000542934999884892
}
}
},
"UnityEnvironment.step": {
"total": 0.030023830999880374,
"count": 1,
"is_parallel": true,
"self": 0.00034061199971802125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019580400021368405,
"count": 1,
"is_parallel": true,
"self": 0.00019580400021368405
},
"communicator.exchange": {
"total": 0.02877021899985266,
"count": 1,
"is_parallel": true,
"self": 0.02877021899985266
},
"steps_from_proto": {
"total": 0.0007171960000960098,
"count": 1,
"is_parallel": true,
"self": 0.00018631499983712274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005308810002588871,
"count": 2,
"is_parallel": true,
"self": 0.0005308810002588871
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1196.922904385844,
"count": 232780,
"is_parallel": true,
"self": 36.52662366796994,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.1019338709873,
"count": 232780,
"is_parallel": true,
"self": 78.1019338709873
},
"communicator.exchange": {
"total": 997.1024184708804,
"count": 232780,
"is_parallel": true,
"self": 997.1024184708804
},
"steps_from_proto": {
"total": 85.19192837600644,
"count": 232780,
"is_parallel": true,
"self": 30.107590144124742,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.0843382318817,
"count": 465560,
"is_parallel": true,
"self": 55.0843382318817
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.28399089689856,
"count": 232781,
"self": 6.264117633862043,
"children": {
"process_trajectory": {
"total": 158.00828609003702,
"count": 232781,
"self": 156.75835116603685,
"children": {
"RLTrainer._checkpoint": {
"total": 1.249934924000172,
"count": 10,
"self": 1.249934924000172
}
}
},
"_update_policy": {
"total": 328.0115871729995,
"count": 97,
"self": 261.47040667497936,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.54118049802014,
"count": 2910,
"self": 66.54118049802014
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0049998309114017e-06,
"count": 1,
"self": 1.0049998309114017e-06
},
"TrainerController._save_models": {
"total": 0.12000102699994386,
"count": 1,
"self": 0.0018572079998193658,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1181438190001245,
"count": 1,
"self": 0.1181438190001245
}
}
}
}
}
}
}