ppo-Huggy / run_logs /timers.json
sswt's picture
Huggy
96972e6 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4029653072357178,
"min": 1.4029653072357178,
"max": 1.4275767803192139,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69610.9296875,
"min": 67711.7734375,
"max": 78950.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.64716312056737,
"min": 82.48080133555926,
"max": 405.9349593495935,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49433.0,
"min": 48942.0,
"max": 49933.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999937.0,
"min": 49369.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999937.0,
"min": 49369.0,
"max": 1999937.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4152255058288574,
"min": 0.14400513470172882,
"max": 2.491044759750366,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1362.1871337890625,
"min": 17.568626403808594,
"max": 1447.4737548828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6331867758475296,
"min": 1.8669818455322844,
"max": 3.8828969457635174,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2049.1173415780067,
"min": 227.7717851549387,
"max": 2306.1124108433723,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6331867758475296,
"min": 1.8669818455322844,
"max": 3.8828969457635174,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2049.1173415780067,
"min": 227.7717851549387,
"max": 2306.1124108433723,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015625850446586913,
"min": 0.013056803782622714,
"max": 0.020283152143626165,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04687755133976074,
"min": 0.026113607565245427,
"max": 0.06048464049381437,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053871076388491514,
"min": 0.022246104571968316,
"max": 0.05960567891597748,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16161322916547455,
"min": 0.04449220914393663,
"max": 0.17881703674793242,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1202489599499987e-06,
"min": 3.1202489599499987e-06,
"max": 0.000295323001559,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.360746879849996e-06,
"min": 9.360746879849996e-06,
"max": 0.0008439114186961998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104005000000003,
"min": 0.10104005000000003,
"max": 0.1984410000000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031201500000001,
"min": 0.20725714999999997,
"max": 0.5813037999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.1898495e-05,
"min": 6.1898495e-05,
"max": 0.004922205899999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018569548499999998,
"min": 0.00018569548499999998,
"max": 0.014067059619999999,
"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": "1718284710",
"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=Huggy2 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718287444"
},
"total": 2734.274568688,
"count": 1,
"self": 0.5431655460001821,
"children": {
"run_training.setup": {
"total": 0.05670993599994745,
"count": 1,
"self": 0.05670993599994745
},
"TrainerController.start_learning": {
"total": 2733.6746932059996,
"count": 1,
"self": 4.99576142897422,
"children": {
"TrainerController._reset_env": {
"total": 3.1559604199999285,
"count": 1,
"self": 3.1559604199999285
},
"TrainerController.advance": {
"total": 2725.383568537025,
"count": 232311,
"self": 5.183549520861561,
"children": {
"env_step": {
"total": 2169.3893141830026,
"count": 232311,
"self": 1789.1043972039574,
"children": {
"SubprocessEnvManager._take_step": {
"total": 376.7993987610539,
"count": 232311,
"self": 19.76012846088304,
"children": {
"TorchPolicy.evaluate": {
"total": 357.03927030017087,
"count": 222930,
"self": 357.03927030017087
}
}
},
"workers": {
"total": 3.485518217991398,
"count": 232311,
"self": 0.0,
"children": {
"worker_root": {
"total": 2725.569371307018,
"count": 232311,
"is_parallel": true,
"self": 1285.926281143938,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000914054000077158,
"count": 1,
"is_parallel": true,
"self": 0.00021474499999385444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006993090000833035,
"count": 2,
"is_parallel": true,
"self": 0.0006993090000833035
}
}
},
"UnityEnvironment.step": {
"total": 0.03311853399998199,
"count": 1,
"is_parallel": true,
"self": 0.0004160769999543845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021376799998051865,
"count": 1,
"is_parallel": true,
"self": 0.00021376799998051865
},
"communicator.exchange": {
"total": 0.031668278999973154,
"count": 1,
"is_parallel": true,
"self": 0.031668278999973154
},
"steps_from_proto": {
"total": 0.0008204100000739345,
"count": 1,
"is_parallel": true,
"self": 0.00020676799999819195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006136420000757425,
"count": 2,
"is_parallel": true,
"self": 0.0006136420000757425
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1439.6430901630802,
"count": 232310,
"is_parallel": true,
"self": 42.83399343822816,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 97.52354767294992,
"count": 232310,
"is_parallel": true,
"self": 97.52354767294992
},
"communicator.exchange": {
"total": 1196.7422741189616,
"count": 232310,
"is_parallel": true,
"self": 1196.7422741189616
},
"steps_from_proto": {
"total": 102.54327493294045,
"count": 232310,
"is_parallel": true,
"self": 39.20568461792834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.33759031501211,
"count": 464620,
"is_parallel": true,
"self": 63.33759031501211
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 550.8107048331609,
"count": 232311,
"self": 7.25778145304605,
"children": {
"process_trajectory": {
"total": 179.0211304131151,
"count": 232311,
"self": 177.3782257421143,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6429046710007924,
"count": 10,
"self": 1.6429046710007924
}
}
},
"_update_policy": {
"total": 364.5317929669998,
"count": 97,
"self": 298.8371458990041,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.69464706799567,
"count": 2910,
"self": 65.69464706799567
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.1394017550001081,
"count": 1,
"self": 0.0027553120003176446,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13664644299979045,
"count": 1,
"self": 0.13664644299979045
}
}
}
}
}
}
}