ppo-Huggy / run_logs /timers.json
MarcLinder's picture
Huggy
199a648 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4043190479278564,
"min": 1.4043190479278564,
"max": 1.4268860816955566,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72256.4296875,
"min": 68547.953125,
"max": 78162.4765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 116.02594339622641,
"min": 93.59735349716446,
"max": 380.74045801526717,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49195.0,
"min": 49128.0,
"max": 50236.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999551.0,
"min": 49839.0,
"max": 1999551.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999551.0,
"min": 49839.0,
"max": 1999551.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2967967987060547,
"min": 0.12077219039201736,
"max": 2.3750412464141846,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 973.841796875,
"min": 15.700385093688965,
"max": 1207.2686767578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4899409046431757,
"min": 1.8757904420678433,
"max": 3.8949775254555763,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1479.7349435687065,
"min": 243.85275746881962,
"max": 1964.7208099365234,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4899409046431757,
"min": 1.8757904420678433,
"max": 3.8949775254555763,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1479.7349435687065,
"min": 243.85275746881962,
"max": 1964.7208099365234,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017326037592526215,
"min": 0.013818784560256366,
"max": 0.019393192320906867,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03465207518505243,
"min": 0.027637569120512732,
"max": 0.055521202099043876,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.039481360403199994,
"min": 0.022225995703289904,
"max": 0.054597086769839126,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07896272080639999,
"min": 0.04445199140657981,
"max": 0.15089453384280205,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.379498540199999e-06,
"min": 4.379498540199999e-06,
"max": 0.00029533560155479993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.758997080399999e-06,
"min": 8.758997080399999e-06,
"max": 0.0008440053186648998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014598,
"min": 0.1014598,
"max": 0.19844520000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2029196,
"min": 0.2029196,
"max": 0.5813351000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.284402000000002e-05,
"min": 8.284402000000002e-05,
"max": 0.00492241548,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016568804000000005,
"min": 0.00016568804000000005,
"max": 0.014068621490000002,
"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": "1704914558",
"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": "1704918460"
},
"total": 3901.950565351,
"count": 1,
"self": 0.552456556999914,
"children": {
"run_training.setup": {
"total": 0.06316485900003954,
"count": 1,
"self": 0.06316485900003954
},
"TrainerController.start_learning": {
"total": 3901.334943935,
"count": 1,
"self": 6.848149501003718,
"children": {
"TrainerController._reset_env": {
"total": 3.7281062079999856,
"count": 1,
"self": 3.7281062079999856
},
"TrainerController.advance": {
"total": 3890.650624151996,
"count": 230971,
"self": 7.324473215918715,
"children": {
"env_step": {
"total": 2488.8078222700215,
"count": 230971,
"self": 2076.505484555124,
"children": {
"SubprocessEnvManager._take_step": {
"total": 407.7157293970249,
"count": 230971,
"self": 24.332360867112584,
"children": {
"TorchPolicy.evaluate": {
"total": 383.38336852991233,
"count": 223113,
"self": 383.38336852991233
}
}
},
"workers": {
"total": 4.58660831787256,
"count": 230971,
"self": 0.0,
"children": {
"worker_root": {
"total": 3889.400046988004,
"count": 230971,
"is_parallel": true,
"self": 2236.3021962988914,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007698040000150286,
"count": 1,
"is_parallel": true,
"self": 0.0002027059999818448,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005670980000331838,
"count": 2,
"is_parallel": true,
"self": 0.0005670980000331838
}
}
},
"UnityEnvironment.step": {
"total": 0.0365557179999314,
"count": 1,
"is_parallel": true,
"self": 0.000387128999932429,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00016480800002227625,
"count": 1,
"is_parallel": true,
"self": 0.00016480800002227625
},
"communicator.exchange": {
"total": 0.03509743199992954,
"count": 1,
"is_parallel": true,
"self": 0.03509743199992954
},
"steps_from_proto": {
"total": 0.0009063490000471575,
"count": 1,
"is_parallel": true,
"self": 0.00023061299998516915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006757360000619883,
"count": 2,
"is_parallel": true,
"self": 0.0006757360000619883
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1653.0978506891124,
"count": 230970,
"is_parallel": true,
"self": 53.121881980227954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.59496561104527,
"count": 230970,
"is_parallel": true,
"self": 84.59496561104527
},
"communicator.exchange": {
"total": 1393.3146160448823,
"count": 230970,
"is_parallel": true,
"self": 1393.3146160448823
},
"steps_from_proto": {
"total": 122.06638705295711,
"count": 230970,
"is_parallel": true,
"self": 40.055460741827346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.01092631112977,
"count": 461940,
"is_parallel": true,
"self": 82.01092631112977
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1394.5183286660558,
"count": 230971,
"self": 10.941266363975501,
"children": {
"process_trajectory": {
"total": 215.79293883607977,
"count": 230971,
"self": 215.13854128307923,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6543975530005355,
"count": 6,
"self": 0.6543975530005355
}
}
},
"_update_policy": {
"total": 1167.7841234660004,
"count": 96,
"self": 314.3505426719855,
"children": {
"TorchPPOOptimizer.update": {
"total": 853.4335807940149,
"count": 2880,
"self": 853.4335807940149
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4590004866477102e-06,
"count": 1,
"self": 1.4590004866477102e-06
},
"TrainerController._save_models": {
"total": 0.1080626149996533,
"count": 1,
"self": 0.0028957279992027907,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10516688700045052,
"count": 1,
"self": 0.10516688700045052
}
}
}
}
}
}
}