ppo-Huggy / run_logs /timers.json
Chhabi's picture
Huggy
31f82dc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.408771276473999,
"min": 1.408771276473999,
"max": 1.4284006357192993,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69101.640625,
"min": 69101.640625,
"max": 78169.7578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.65469061876247,
"min": 81.8658940397351,
"max": 399.416,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49426.0,
"min": 48786.0,
"max": 50348.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49689.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49689.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3210136890411377,
"min": 0.15432828664779663,
"max": 2.5151236057281494,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1162.827880859375,
"min": 19.136707305908203,
"max": 1427.091064453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.531210827256391,
"min": 1.8401704180625178,
"max": 3.954984633335427,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1769.136624455452,
"min": 228.1811318397522,
"max": 2264.314527094364,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.531210827256391,
"min": 1.8401704180625178,
"max": 3.954984633335427,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1769.136624455452,
"min": 228.1811318397522,
"max": 2264.314527094364,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014877061009368238,
"min": 0.011829395534247548,
"max": 0.020869784740655935,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.029754122018736475,
"min": 0.023658791068495097,
"max": 0.058573501289356504,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04792698957026005,
"min": 0.01988388014336427,
"max": 0.06201500673260953,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0958539791405201,
"min": 0.03976776028672854,
"max": 0.1860450201978286,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.602023466024996e-06,
"min": 4.602023466024996e-06,
"max": 0.0002952887265704249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.204046932049993e-06,
"min": 9.204046932049993e-06,
"max": 0.0008438122687292499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101533975,
"min": 0.101533975,
"max": 0.19842957500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20306795,
"min": 0.20306795,
"max": 0.58127075,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.654535249999991e-05,
"min": 8.654535249999991e-05,
"max": 0.0049216357925,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017309070499999982,
"min": 0.00017309070499999982,
"max": 0.014065410425,
"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": "1714551880",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714556490"
},
"total": 4610.180899272001,
"count": 1,
"self": 1.0335420600013094,
"children": {
"run_training.setup": {
"total": 0.07089216399992893,
"count": 1,
"self": 0.07089216399992893
},
"TrainerController.start_learning": {
"total": 4609.076465048,
"count": 1,
"self": 8.710588405033377,
"children": {
"TrainerController._reset_env": {
"total": 3.2197460799999362,
"count": 1,
"self": 3.2197460799999362
},
"TrainerController.advance": {
"total": 4596.904424158966,
"count": 232181,
"self": 8.20644768704824,
"children": {
"env_step": {
"total": 2997.16785313191,
"count": 232181,
"self": 2509.715231115997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 482.17163436302724,
"count": 232181,
"self": 31.428499770097915,
"children": {
"TorchPolicy.evaluate": {
"total": 450.7431345929293,
"count": 223000,
"self": 450.7431345929293
}
}
},
"workers": {
"total": 5.280987652885642,
"count": 232181,
"self": 0.0,
"children": {
"worker_root": {
"total": 4596.042338444042,
"count": 232181,
"is_parallel": true,
"self": 2599.5620570260953,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011135119999607923,
"count": 1,
"is_parallel": true,
"self": 0.00031806100002995663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007954509999308357,
"count": 2,
"is_parallel": true,
"self": 0.0007954509999308357
}
}
},
"UnityEnvironment.step": {
"total": 0.036157634999995025,
"count": 1,
"is_parallel": true,
"self": 0.00045811799986950064,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023756400003094313,
"count": 1,
"is_parallel": true,
"self": 0.00023756400003094313
},
"communicator.exchange": {
"total": 0.03455095200001779,
"count": 1,
"is_parallel": true,
"self": 0.03455095200001779
},
"steps_from_proto": {
"total": 0.0009110010000767943,
"count": 1,
"is_parallel": true,
"self": 0.0002488800000719493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000662121000004845,
"count": 2,
"is_parallel": true,
"self": 0.000662121000004845
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1996.4802814179466,
"count": 232180,
"is_parallel": true,
"self": 61.99337610208022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 110.19952612190093,
"count": 232180,
"is_parallel": true,
"self": 110.19952612190093
},
"communicator.exchange": {
"total": 1686.0474929460067,
"count": 232180,
"is_parallel": true,
"self": 1686.0474929460067
},
"steps_from_proto": {
"total": 138.23988624795868,
"count": 232180,
"is_parallel": true,
"self": 44.97174300113306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.26814324682562,
"count": 464360,
"is_parallel": true,
"self": 93.26814324682562
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1591.5301233400082,
"count": 232181,
"self": 13.060959390023527,
"children": {
"process_trajectory": {
"total": 250.9480768709849,
"count": 232181,
"self": 249.6616182039844,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2864586670004883,
"count": 10,
"self": 1.2864586670004883
}
}
},
"_update_policy": {
"total": 1327.5210870789997,
"count": 96,
"self": 335.0591823529802,
"children": {
"TorchPPOOptimizer.update": {
"total": 992.4619047260195,
"count": 2880,
"self": 992.4619047260195
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.525000698165968e-06,
"count": 1,
"self": 1.525000698165968e-06
},
"TrainerController._save_models": {
"total": 0.24170487899937143,
"count": 1,
"self": 0.012041900999065547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22966297800030588,
"count": 1,
"self": 0.22966297800030588
}
}
}
}
}
}
}