ppo-Huggy / run_logs /timers.json
Rhythm's picture
Huggy
92bda7b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4012715816497803,
"min": 1.4012715816497803,
"max": 1.426793098449707,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71576.953125,
"min": 67804.6015625,
"max": 78539.09375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.34323432343234,
"min": 80.22077922077922,
"max": 398.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49294.0,
"min": 49294.0,
"max": 50235.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49714.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49714.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4076502323150635,
"min": 0.04005030170083046,
"max": 2.4449942111968994,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1459.0360107421875,
"min": 5.006287574768066,
"max": 1462.455322265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7817321117758356,
"min": 1.799029324054718,
"max": 3.8795508052982237,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2291.7296597361565,
"min": 224.87866550683975,
"max": 2299.0909678936005,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7817321117758356,
"min": 1.799029324054718,
"max": 3.8795508052982237,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2291.7296597361565,
"min": 224.87866550683975,
"max": 2299.0909678936005,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016407504007899358,
"min": 0.014676866361211675,
"max": 0.01998789637242832,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.049222512023698074,
"min": 0.02935373272242335,
"max": 0.05830911879408329,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05962078198790551,
"min": 0.023350654480357964,
"max": 0.059780180040333,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17886234596371653,
"min": 0.04670130896071593,
"max": 0.179340540120999,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.789198736966667e-06,
"min": 3.789198736966667e-06,
"max": 0.000295308826563725,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1367596210900001e-05,
"min": 1.1367596210900001e-05,
"max": 0.0008441896686034499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126303333333336,
"min": 0.10126303333333336,
"max": 0.19843627500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037891000000001,
"min": 0.20766645,
"max": 0.58139655,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.302536333333336e-05,
"min": 7.302536333333336e-05,
"max": 0.004921970122500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002190760900000001,
"min": 0.0002190760900000001,
"max": 0.014071687844999996,
"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": "1754286919",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1754289419"
},
"total": 2500.233790841,
"count": 1,
"self": 0.4363495160000639,
"children": {
"run_training.setup": {
"total": 0.018320362999929785,
"count": 1,
"self": 0.018320362999929785
},
"TrainerController.start_learning": {
"total": 2499.779120962,
"count": 1,
"self": 4.272657140927095,
"children": {
"TrainerController._reset_env": {
"total": 2.9778233679999175,
"count": 1,
"self": 2.9778233679999175
},
"TrainerController.advance": {
"total": 2492.4280560830725,
"count": 232403,
"self": 4.4078111243698,
"children": {
"env_step": {
"total": 1989.6026641669332,
"count": 232403,
"self": 1575.0955961565169,
"children": {
"SubprocessEnvManager._take_step": {
"total": 411.827790604214,
"count": 232403,
"self": 15.460100186349337,
"children": {
"TorchPolicy.evaluate": {
"total": 396.36769041786465,
"count": 222993,
"self": 396.36769041786465
}
}
},
"workers": {
"total": 2.6792774062023454,
"count": 232403,
"self": 0.0,
"children": {
"worker_root": {
"total": 2492.2920106151637,
"count": 232403,
"is_parallel": true,
"self": 1205.1147996511859,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010621700002957368,
"count": 1,
"is_parallel": true,
"self": 0.00029883400065955357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007633359996361833,
"count": 2,
"is_parallel": true,
"self": 0.0007633359996361833
}
}
},
"UnityEnvironment.step": {
"total": 0.029103946999839536,
"count": 1,
"is_parallel": true,
"self": 0.00028311200003372505,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019062399996983004,
"count": 1,
"is_parallel": true,
"self": 0.00019062399996983004
},
"communicator.exchange": {
"total": 0.027942612000060763,
"count": 1,
"is_parallel": true,
"self": 0.027942612000060763
},
"steps_from_proto": {
"total": 0.0006875989997752185,
"count": 1,
"is_parallel": true,
"self": 0.00019381399988560588,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004937849998896127,
"count": 2,
"is_parallel": true,
"self": 0.0004937849998896127
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.1772109639778,
"count": 232402,
"is_parallel": true,
"self": 37.33003459872725,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.79572855800689,
"count": 232402,
"is_parallel": true,
"self": 83.79572855800689
},
"communicator.exchange": {
"total": 1077.410218262131,
"count": 232402,
"is_parallel": true,
"self": 1077.410218262131
},
"steps_from_proto": {
"total": 88.64122954511276,
"count": 232402,
"is_parallel": true,
"self": 33.52210289603272,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.119126649080044,
"count": 464804,
"is_parallel": true,
"self": 55.119126649080044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 498.4175807917695,
"count": 232403,
"self": 6.205436503554665,
"children": {
"process_trajectory": {
"total": 162.39004534021706,
"count": 232403,
"self": 161.08461974621696,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3054255940000985,
"count": 10,
"self": 1.3054255940000985
}
}
},
"_update_policy": {
"total": 329.8220989479978,
"count": 97,
"self": 266.74053417397226,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.08156477402554,
"count": 2910,
"self": 63.08156477402554
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.780005711945705e-07,
"count": 1,
"self": 9.780005711945705e-07
},
"TrainerController._save_models": {
"total": 0.10058339199986222,
"count": 1,
"self": 0.0015502390006076894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09903315299925453,
"count": 1,
"self": 0.09903315299925453
}
}
}
}
}
}
}