ppo-Huggy / run_logs /timers.json
BearSubj13's picture
Huggy
5441cd8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4100059270858765,
"min": 1.4100059270858765,
"max": 1.4301559925079346,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72446.1015625,
"min": 67975.765625,
"max": 77418.1953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 118.28909952606635,
"min": 89.00718132854578,
"max": 395.53543307086613,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49918.0,
"min": 48984.0,
"max": 50233.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999688.0,
"min": 49828.0,
"max": 1999688.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999688.0,
"min": 49828.0,
"max": 1999688.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3053531646728516,
"min": 0.19879621267318726,
"max": 2.4127860069274902,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 972.8590698242188,
"min": 25.048322677612305,
"max": 1283.75244140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4789134371337167,
"min": 1.85780017456365,
"max": 3.922638792288541,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1468.1014704704285,
"min": 234.0828219950199,
"max": 2065.5188625454903,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4789134371337167,
"min": 1.85780017456365,
"max": 3.922638792288541,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1468.1014704704285,
"min": 234.0828219950199,
"max": 2065.5188625454903,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01870554411175868,
"min": 0.013640284339150335,
"max": 0.020084179092464183,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056116632335276036,
"min": 0.02728056867830067,
"max": 0.056116632335276036,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048484708989659946,
"min": 0.0203588118776679,
"max": 0.054678185739450984,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14545412696897983,
"min": 0.0407176237553358,
"max": 0.16403455721835294,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.24254891918333e-06,
"min": 3.24254891918333e-06,
"max": 0.000295360426546525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.72764675754999e-06,
"min": 9.72764675754999e-06,
"max": 0.0008441703186099,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108081666666667,
"min": 0.10108081666666667,
"max": 0.198453475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30324245,
"min": 0.20730470000000006,
"max": 0.5813901,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.393275166666662e-05,
"min": 6.393275166666662e-05,
"max": 0.004922828402499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019179825499999987,
"min": 0.00019179825499999987,
"max": 0.014071365989999998,
"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": "1740738065",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740740499"
},
"total": 2434.672862823,
"count": 1,
"self": 0.44356732899950657,
"children": {
"run_training.setup": {
"total": 0.023449736000202392,
"count": 1,
"self": 0.023449736000202392
},
"TrainerController.start_learning": {
"total": 2434.205845758,
"count": 1,
"self": 4.37199380607899,
"children": {
"TrainerController._reset_env": {
"total": 3.257597229000112,
"count": 1,
"self": 3.257597229000112
},
"TrainerController.advance": {
"total": 2426.4587459239215,
"count": 231294,
"self": 4.5884897474593345,
"children": {
"env_step": {
"total": 1928.7859783238123,
"count": 231294,
"self": 1513.1768931911174,
"children": {
"SubprocessEnvManager._take_step": {
"total": 412.9928376538469,
"count": 231294,
"self": 15.597041671643638,
"children": {
"TorchPolicy.evaluate": {
"total": 397.39579598220325,
"count": 223124,
"self": 397.39579598220325
}
}
},
"workers": {
"total": 2.6162474788479813,
"count": 231294,
"self": 0.0,
"children": {
"worker_root": {
"total": 2426.8055654420687,
"count": 231294,
"is_parallel": true,
"self": 1192.7244768571109,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001024213000164309,
"count": 1,
"is_parallel": true,
"self": 0.00021374000016294303,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000810473000001366,
"count": 2,
"is_parallel": true,
"self": 0.000810473000001366
}
}
},
"UnityEnvironment.step": {
"total": 0.028544732999762346,
"count": 1,
"is_parallel": true,
"self": 0.00030762300002606935,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019119599983241642,
"count": 1,
"is_parallel": true,
"self": 0.00019119599983241642
},
"communicator.exchange": {
"total": 0.02732585800004017,
"count": 1,
"is_parallel": true,
"self": 0.02732585800004017
},
"steps_from_proto": {
"total": 0.0007200559998636891,
"count": 1,
"is_parallel": true,
"self": 0.00020065799981239252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005193980000512965,
"count": 2,
"is_parallel": true,
"self": 0.0005193980000512965
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1234.0810885849578,
"count": 231293,
"is_parallel": true,
"self": 36.76966034087718,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.00576810715711,
"count": 231293,
"is_parallel": true,
"self": 79.00576810715711
},
"communicator.exchange": {
"total": 1032.6425242057594,
"count": 231293,
"is_parallel": true,
"self": 1032.6425242057594
},
"steps_from_proto": {
"total": 85.6631359311641,
"count": 231293,
"is_parallel": true,
"self": 29.53402784196669,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.129108089197416,
"count": 462586,
"is_parallel": true,
"self": 56.129108089197416
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.08427785264985,
"count": 231294,
"self": 6.676086794653656,
"children": {
"process_trajectory": {
"total": 153.83748307799488,
"count": 231294,
"self": 152.59854784899426,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2389352290006173,
"count": 10,
"self": 1.2389352290006173
}
}
},
"_update_policy": {
"total": 332.5707079800013,
"count": 97,
"self": 266.1347673350051,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.43594064499621,
"count": 2910,
"self": 66.43594064499621
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2299997251830064e-06,
"count": 1,
"self": 1.2299997251830064e-06
},
"TrainerController._save_models": {
"total": 0.11750756899982662,
"count": 1,
"self": 0.0018472729998393334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11566029599998728,
"count": 1,
"self": 0.11566029599998728
}
}
}
}
}
}
}