ppo-Huggy / run_logs /timers.json
Nikhil058's picture
Huggy
a512530
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4033538103103638,
"min": 1.4033538103103638,
"max": 1.4263288974761963,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69042.203125,
"min": 67978.890625,
"max": 76897.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.48514851485149,
"min": 83.03361344537815,
"max": 419.18333333333334,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49735.0,
"min": 48889.0,
"max": 50302.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999491.0,
"min": 49851.0,
"max": 1999491.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999491.0,
"min": 49851.0,
"max": 1999491.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.339779853820801,
"min": 0.05316059663891792,
"max": 2.4749395847320557,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1181.5888671875,
"min": 6.32611083984375,
"max": 1472.589111328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4914526034109663,
"min": 1.8471388030452889,
"max": 3.9453312861508336,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1763.183564722538,
"min": 219.80951756238937,
"max": 2308.174365103245,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4914526034109663,
"min": 1.8471388030452889,
"max": 3.9453312861508336,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1763.183564722538,
"min": 219.80951756238937,
"max": 2308.174365103245,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016703785408592214,
"min": 0.013160638008169676,
"max": 0.019180349233405045,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05011135622577664,
"min": 0.02632127601633935,
"max": 0.05378888622459878,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05245897331171565,
"min": 0.022285498678684235,
"max": 0.06261532735079527,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15737691993514696,
"min": 0.04457099735736847,
"max": 0.17513844147324564,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.487298837599991e-06,
"min": 3.487298837599991e-06,
"max": 0.00029531805156065,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0461896512799973e-05,
"min": 1.0461896512799973e-05,
"max": 0.00084383386872205,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116240000000003,
"min": 0.10116240000000003,
"max": 0.19843935000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348720000000007,
"min": 0.20745744999999993,
"max": 0.58127795,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.800375999999983e-05,
"min": 6.800375999999983e-05,
"max": 0.004922123565,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020401127999999949,
"min": 0.00020401127999999949,
"max": 0.014065769705,
"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": "1693155498",
"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": "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": "1693158155"
},
"total": 2656.662672142,
"count": 1,
"self": 0.7932497000001604,
"children": {
"run_training.setup": {
"total": 0.06910858200001258,
"count": 1,
"self": 0.06910858200001258
},
"TrainerController.start_learning": {
"total": 2655.8003138599997,
"count": 1,
"self": 5.015222961045765,
"children": {
"TrainerController._reset_env": {
"total": 4.823462608999989,
"count": 1,
"self": 4.823462608999989
},
"TrainerController.advance": {
"total": 2645.7502899079545,
"count": 232001,
"self": 5.345814657069241,
"children": {
"env_step": {
"total": 2064.6604394049177,
"count": 232001,
"self": 1746.4322161818664,
"children": {
"SubprocessEnvManager._take_step": {
"total": 314.992367343149,
"count": 232001,
"self": 18.62110754310652,
"children": {
"TorchPolicy.evaluate": {
"total": 296.3712598000425,
"count": 222996,
"self": 296.3712598000425
}
}
},
"workers": {
"total": 3.2358558799022603,
"count": 232001,
"self": 0.0,
"children": {
"worker_root": {
"total": 2647.2712078181194,
"count": 232001,
"is_parallel": true,
"self": 1224.385196386154,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012439749999657579,
"count": 1,
"is_parallel": true,
"self": 0.0003986890000078347,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008452859999579232,
"count": 2,
"is_parallel": true,
"self": 0.0008452859999579232
}
}
},
"UnityEnvironment.step": {
"total": 0.031728400000019974,
"count": 1,
"is_parallel": true,
"self": 0.00042898399999558023,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025308099998255784,
"count": 1,
"is_parallel": true,
"self": 0.00025308099998255784
},
"communicator.exchange": {
"total": 0.030109685000070385,
"count": 1,
"is_parallel": true,
"self": 0.030109685000070385
},
"steps_from_proto": {
"total": 0.0009366499999714506,
"count": 1,
"is_parallel": true,
"self": 0.00026838399992357154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006682660000478791,
"count": 2,
"is_parallel": true,
"self": 0.0006682660000478791
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1422.8860114319655,
"count": 232000,
"is_parallel": true,
"self": 42.223729777114386,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.97476517592156,
"count": 232000,
"is_parallel": true,
"self": 89.97476517592156
},
"communicator.exchange": {
"total": 1184.313560653913,
"count": 232000,
"is_parallel": true,
"self": 1184.313560653913
},
"steps_from_proto": {
"total": 106.37395582501631,
"count": 232000,
"is_parallel": true,
"self": 39.8415298601268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.53242596488951,
"count": 464000,
"is_parallel": true,
"self": 66.53242596488951
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 575.7440358459675,
"count": 232001,
"self": 7.252337728948191,
"children": {
"process_trajectory": {
"total": 149.3659261350184,
"count": 232001,
"self": 147.75967199401873,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6062541409996811,
"count": 10,
"self": 1.6062541409996811
}
}
},
"_update_policy": {
"total": 419.12577198200086,
"count": 97,
"self": 357.4888777670119,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.636894214988956,
"count": 2910,
"self": 61.636894214988956
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5189998521236703e-06,
"count": 1,
"self": 1.5189998521236703e-06
},
"TrainerController._save_models": {
"total": 0.2113368629998149,
"count": 1,
"self": 0.003181181999934779,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20815568099988013,
"count": 1,
"self": 0.20815568099988013
}
}
}
}
}
}
}