ppo-Huggy / run_logs /timers.json
Cicikush's picture
Huggy
a35d979 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402917742729187,
"min": 1.402917742729187,
"max": 1.4281224012374878,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70519.0625,
"min": 68072.8828125,
"max": 77201.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.36513157894737,
"min": 77.94794952681389,
"max": 390.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49470.0,
"min": 49325.0,
"max": 50161.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999971.0,
"min": 49942.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999971.0,
"min": 49942.0,
"max": 1999971.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4753525257110596,
"min": 0.07345788180828094,
"max": 2.489096164703369,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1505.0142822265625,
"min": 9.329151153564453,
"max": 1568.830322265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8460888114610783,
"min": 1.7165934865868937,
"max": 3.986936341990069,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2338.4219973683357,
"min": 218.0073727965355,
"max": 2473.924679338932,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8460888114610783,
"min": 1.7165934865868937,
"max": 3.986936341990069,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2338.4219973683357,
"min": 218.0073727965355,
"max": 2473.924679338932,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014810469857022529,
"min": 0.01315215049459463,
"max": 0.020518757135141643,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04443140957106759,
"min": 0.02630430098918926,
"max": 0.061556271405424925,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05556631460785866,
"min": 0.022255518939346075,
"max": 0.06768277511000634,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16669894382357597,
"min": 0.04451103787869215,
"max": 0.19197013651331268,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7289987570333225e-06,
"min": 3.7289987570333225e-06,
"max": 0.000295303426565525,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1186996271099968e-05,
"min": 1.1186996271099968e-05,
"max": 0.0008438691187102996,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124296666666666,
"min": 0.10124296666666666,
"max": 0.198434475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30372889999999997,
"min": 0.2076427,
"max": 0.5812897,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.202403666666652e-05,
"min": 7.202403666666652e-05,
"max": 0.004921880302500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021607210999999955,
"min": 0.00021607210999999955,
"max": 0.01406635603,
"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": "1747211887",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747214357"
},
"total": 2470.5182080330005,
"count": 1,
"self": 0.4893721880002886,
"children": {
"run_training.setup": {
"total": 0.023248816999966948,
"count": 1,
"self": 0.023248816999966948
},
"TrainerController.start_learning": {
"total": 2470.0055870280003,
"count": 1,
"self": 4.499744552778338,
"children": {
"TrainerController._reset_env": {
"total": 3.3762657679999393,
"count": 1,
"self": 3.3762657679999393
},
"TrainerController.advance": {
"total": 2462.014465835222,
"count": 232651,
"self": 4.718086714119636,
"children": {
"env_step": {
"total": 1964.2745517389815,
"count": 232651,
"self": 1541.1749441561903,
"children": {
"SubprocessEnvManager._take_step": {
"total": 420.44680641185687,
"count": 232651,
"self": 16.191025666990072,
"children": {
"TorchPolicy.evaluate": {
"total": 404.2557807448668,
"count": 222923,
"self": 404.2557807448668
}
}
},
"workers": {
"total": 2.6528011709342536,
"count": 232651,
"self": 0.0,
"children": {
"worker_root": {
"total": 2462.700953290851,
"count": 232651,
"is_parallel": true,
"self": 1206.5343568518708,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009496239999862155,
"count": 1,
"is_parallel": true,
"self": 0.00026469300019016373,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006849309997960518,
"count": 2,
"is_parallel": true,
"self": 0.0006849309997960518
}
}
},
"UnityEnvironment.step": {
"total": 0.030703086999892548,
"count": 1,
"is_parallel": true,
"self": 0.00037280099991221505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000211219999982859,
"count": 1,
"is_parallel": true,
"self": 0.000211219999982859
},
"communicator.exchange": {
"total": 0.029337745000020732,
"count": 1,
"is_parallel": true,
"self": 0.029337745000020732
},
"steps_from_proto": {
"total": 0.0007813209999767423,
"count": 1,
"is_parallel": true,
"self": 0.00020008499996038154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005812360000163608,
"count": 2,
"is_parallel": true,
"self": 0.0005812360000163608
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1256.1665964389802,
"count": 232650,
"is_parallel": true,
"self": 37.25611007606358,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.59355797387275,
"count": 232650,
"is_parallel": true,
"self": 82.59355797387275
},
"communicator.exchange": {
"total": 1047.6647513680023,
"count": 232650,
"is_parallel": true,
"self": 1047.6647513680023
},
"steps_from_proto": {
"total": 88.65217702104155,
"count": 232650,
"is_parallel": true,
"self": 32.94212104318444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.71005597785711,
"count": 465300,
"is_parallel": true,
"self": 55.71005597785711
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.02182738212105,
"count": 232651,
"self": 6.914485094027668,
"children": {
"process_trajectory": {
"total": 166.25710950809275,
"count": 232651,
"self": 164.95576409209252,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3013454160002311,
"count": 10,
"self": 1.3013454160002311
}
}
},
"_update_policy": {
"total": 319.8502327800006,
"count": 97,
"self": 255.28904641800682,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.5611863619938,
"count": 2910,
"self": 64.5611863619938
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2810000953322742e-06,
"count": 1,
"self": 1.2810000953322742e-06
},
"TrainerController._save_models": {
"total": 0.11510959099996398,
"count": 1,
"self": 0.001550780999878043,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11355881000008594,
"count": 1,
"self": 0.11355881000008594
}
}
}
}
}
}
}