ppo-Huggy / run_logs /timers.json
nullne's picture
Huggy
878e57e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4105112552642822,
"min": 1.4105112552642822,
"max": 1.433327555656433,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70717.390625,
"min": 68874.7421875,
"max": 78115.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.88911290322581,
"min": 93.79506641366224,
"max": 399.624,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49545.0,
"min": 48922.0,
"max": 50093.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999335.0,
"min": 49603.0,
"max": 1999335.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999335.0,
"min": 49603.0,
"max": 1999335.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.331834316253662,
"min": 0.10409993678331375,
"max": 2.3947713375091553,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1156.58984375,
"min": 12.908391952514648,
"max": 1225.9091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.611946251844206,
"min": 1.730135049550764,
"max": 3.8662328276320967,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1791.5253409147263,
"min": 214.53674614429474,
"max": 1919.596596479416,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.611946251844206,
"min": 1.730135049550764,
"max": 3.8662328276320967,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1791.5253409147263,
"min": 214.53674614429474,
"max": 1919.596596479416,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014750269363867117,
"min": 0.013348289439778052,
"max": 0.021852534056718772,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.029500538727734234,
"min": 0.029500538727734234,
"max": 0.055911515981036546,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05098078449567159,
"min": 0.020913969228665036,
"max": 0.05595556327866183,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10196156899134318,
"min": 0.04182793845733007,
"max": 0.1678666898359855,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.653473448875009e-06,
"min": 4.653473448875009e-06,
"max": 0.0002953632015456,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.306946897750019e-06,
"min": 9.306946897750019e-06,
"max": 0.0008439849186716999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155112500000002,
"min": 0.10155112500000002,
"max": 0.19845439999999992,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20310225000000004,
"min": 0.20310225000000004,
"max": 0.5813283,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.740113750000015e-05,
"min": 8.740113750000015e-05,
"max": 0.004922874560000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001748022750000003,
"min": 0.0001748022750000003,
"max": 0.014068282170000003,
"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": "1705386729",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1705389122"
},
"total": 2392.1371690549995,
"count": 1,
"self": 0.4448191999995288,
"children": {
"run_training.setup": {
"total": 0.06061008199992557,
"count": 1,
"self": 0.06061008199992557
},
"TrainerController.start_learning": {
"total": 2391.631739773,
"count": 1,
"self": 4.3987843509808044,
"children": {
"TrainerController._reset_env": {
"total": 3.8023823179999,
"count": 1,
"self": 3.8023823179999
},
"TrainerController.advance": {
"total": 2383.3188937780187,
"count": 231026,
"self": 4.592033307053498,
"children": {
"env_step": {
"total": 1902.501937962968,
"count": 231026,
"self": 1579.5065473190998,
"children": {
"SubprocessEnvManager._take_step": {
"total": 320.17042390090774,
"count": 231026,
"self": 16.858684522875933,
"children": {
"TorchPolicy.evaluate": {
"total": 303.3117393780318,
"count": 222985,
"self": 303.3117393780318
}
}
},
"workers": {
"total": 2.824966742960555,
"count": 231026,
"self": 0.0,
"children": {
"worker_root": {
"total": 2384.5261526710055,
"count": 231026,
"is_parallel": true,
"self": 1098.045851307006,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007355559999950856,
"count": 1,
"is_parallel": true,
"self": 0.00021469099999649188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005208649999985937,
"count": 2,
"is_parallel": true,
"self": 0.0005208649999985937
}
}
},
"UnityEnvironment.step": {
"total": 0.04663793700001406,
"count": 1,
"is_parallel": true,
"self": 0.0003413250001358392,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002061599999478858,
"count": 1,
"is_parallel": true,
"self": 0.0002061599999478858
},
"communicator.exchange": {
"total": 0.04541434999998728,
"count": 1,
"is_parallel": true,
"self": 0.04541434999998728
},
"steps_from_proto": {
"total": 0.0006761019999430573,
"count": 1,
"is_parallel": true,
"self": 0.00016643899982682342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005096630001162339,
"count": 2,
"is_parallel": true,
"self": 0.0005096630001162339
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1286.4803013639996,
"count": 231025,
"is_parallel": true,
"self": 40.898590595060114,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.4297773659357,
"count": 231025,
"is_parallel": true,
"self": 82.4297773659357
},
"communicator.exchange": {
"total": 1073.6585351179804,
"count": 231025,
"is_parallel": true,
"self": 1073.6585351179804
},
"steps_from_proto": {
"total": 89.49339828502355,
"count": 231025,
"is_parallel": true,
"self": 31.184848982018252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.30854930300529,
"count": 462050,
"is_parallel": true,
"self": 58.30854930300529
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.224922507997,
"count": 231026,
"self": 6.809280737915969,
"children": {
"process_trajectory": {
"total": 145.10894010308095,
"count": 231026,
"self": 143.867379461081,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2415606419999676,
"count": 10,
"self": 1.2415606419999676
}
}
},
"_update_policy": {
"total": 324.3067016670001,
"count": 96,
"self": 261.0531188329925,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.2535828340076,
"count": 2880,
"self": 63.2535828340076
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1729998732334934e-06,
"count": 1,
"self": 1.1729998732334934e-06
},
"TrainerController._save_models": {
"total": 0.11167815300041184,
"count": 1,
"self": 0.002039440000316972,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10963871300009487,
"count": 1,
"self": 0.10963871300009487
}
}
}
}
}
}
}