ppo-Huggy / run_logs /timers.json
Zakia's picture
Huggy
b0d0a8e
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4082750082015991,
"min": 1.4082750082015991,
"max": 1.4242403507232666,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70495.4296875,
"min": 68173.953125,
"max": 76482.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.3144758735441,
"min": 75.33639143730886,
"max": 403.491935483871,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49471.0,
"min": 48719.0,
"max": 50033.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999983.0,
"min": 49544.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999983.0,
"min": 49544.0,
"max": 1999983.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5083184242248535,
"min": -0.0270245298743248,
"max": 2.5215234756469727,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1507.4993896484375,
"min": -3.324017286300659,
"max": 1615.287353515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.886500826691232,
"min": 1.880968809370103,
"max": 4.040870827875396,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2335.7869968414307,
"min": 231.35916355252266,
"max": 2469.860018789768,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.886500826691232,
"min": 1.880968809370103,
"max": 4.040870827875396,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2335.7869968414307,
"min": 231.35916355252266,
"max": 2469.860018789768,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015978201068436546,
"min": 0.013573544530906171,
"max": 0.0198174335851541,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04793460320530964,
"min": 0.027147089061812343,
"max": 0.0594523007554623,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05709475084311433,
"min": 0.023215397416303556,
"max": 0.062111598004897434,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17128425252934298,
"min": 0.04643079483260711,
"max": 0.1863347940146923,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.606448797883335e-06,
"min": 3.606448797883335e-06,
"max": 0.0002953396515534499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0819346393650005e-05,
"min": 1.0819346393650005e-05,
"max": 0.0008440201686599501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120211666666667,
"min": 0.10120211666666667,
"max": 0.19844655,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30360635,
"min": 0.20755590000000002,
"max": 0.58134005,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.998562166666671e-05,
"min": 6.998562166666671e-05,
"max": 0.004922482844999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020995686500000014,
"min": 0.00020995686500000014,
"max": 0.014068868495000001,
"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": "1700338577",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700341001"
},
"total": 2423.5984012930003,
"count": 1,
"self": 0.43742615700057286,
"children": {
"run_training.setup": {
"total": 0.046500501000082295,
"count": 1,
"self": 0.046500501000082295
},
"TrainerController.start_learning": {
"total": 2423.1144746349996,
"count": 1,
"self": 4.418626131079236,
"children": {
"TrainerController._reset_env": {
"total": 9.852871151999807,
"count": 1,
"self": 9.852871151999807
},
"TrainerController.advance": {
"total": 2408.7454761059203,
"count": 232859,
"self": 4.658656838556908,
"children": {
"env_step": {
"total": 1897.5356067162343,
"count": 232859,
"self": 1565.799105979122,
"children": {
"SubprocessEnvManager._take_step": {
"total": 328.9650487220756,
"count": 232859,
"self": 16.76019167802906,
"children": {
"TorchPolicy.evaluate": {
"total": 312.20485704404655,
"count": 222938,
"self": 312.20485704404655
}
}
},
"workers": {
"total": 2.7714520150366297,
"count": 232859,
"self": 0.0,
"children": {
"worker_root": {
"total": 2415.65686966707,
"count": 232859,
"is_parallel": true,
"self": 1143.849835656058,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008571359999223205,
"count": 1,
"is_parallel": true,
"self": 0.00026853599956666585,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005886000003556546,
"count": 2,
"is_parallel": true,
"self": 0.0005886000003556546
}
}
},
"UnityEnvironment.step": {
"total": 0.02744494999978997,
"count": 1,
"is_parallel": true,
"self": 0.00029305699945325614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018577900027594296,
"count": 1,
"is_parallel": true,
"self": 0.00018577900027594296
},
"communicator.exchange": {
"total": 0.026314395000099466,
"count": 1,
"is_parallel": true,
"self": 0.026314395000099466
},
"steps_from_proto": {
"total": 0.0006517189999613038,
"count": 1,
"is_parallel": true,
"self": 0.00017334200038021663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00047837699958108715,
"count": 2,
"is_parallel": true,
"self": 0.00047837699958108715
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1271.807034011012,
"count": 232858,
"is_parallel": true,
"self": 39.87803283698531,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.59099192289023,
"count": 232858,
"is_parallel": true,
"self": 82.59099192289023
},
"communicator.exchange": {
"total": 1060.3934161841503,
"count": 232858,
"is_parallel": true,
"self": 1060.3934161841503
},
"steps_from_proto": {
"total": 88.94459306698627,
"count": 232858,
"is_parallel": true,
"self": 31.138970359943414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.80562270704286,
"count": 465716,
"is_parallel": true,
"self": 57.80562270704286
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 506.5512125511291,
"count": 232859,
"self": 6.272021300132565,
"children": {
"process_trajectory": {
"total": 159.81364770999562,
"count": 232859,
"self": 158.72133754199695,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0923101679986758,
"count": 10,
"self": 1.0923101679986758
}
}
},
"_update_policy": {
"total": 340.4655435410009,
"count": 97,
"self": 278.6791938880083,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.78634965299261,
"count": 2910,
"self": 61.78634965299261
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.480001270072535e-07,
"count": 1,
"self": 8.480001270072535e-07
},
"TrainerController._save_models": {
"total": 0.09750039800019294,
"count": 1,
"self": 0.0017943580005521653,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09570603999964078,
"count": 1,
"self": 0.09570603999964078
}
}
}
}
}
}
}