ppo-Huggy / run_logs /timers.json
lorenzozanetti's picture
Huggy
0c1a391 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402767539024353,
"min": 1.402767539024353,
"max": 1.4258439540863037,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69093.3125,
"min": 67611.2890625,
"max": 77023.453125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 96.31322957198444,
"min": 82.04485049833887,
"max": 425.54237288135596,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49505.0,
"min": 49351.0,
"max": 50214.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49740.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49740.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3410964012145996,
"min": 0.008476171642541885,
"max": 2.4932913780212402,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1203.3236083984375,
"min": 0.9917120337486267,
"max": 1466.5399169921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4725506004192486,
"min": 1.7107756316152394,
"max": 3.9697762755677104,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1784.8910086154938,
"min": 200.160748898983,
"max": 2312.5138980448246,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4725506004192486,
"min": 1.7107756316152394,
"max": 3.9697762755677104,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1784.8910086154938,
"min": 200.160748898983,
"max": 2312.5138980448246,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015567864077941826,
"min": 0.013081349763281954,
"max": 0.019069620587914768,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046703592233825475,
"min": 0.026162699526563908,
"max": 0.057208861763744304,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04979655626747343,
"min": 0.023338062254091102,
"max": 0.05900666769593954,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1493896688024203,
"min": 0.046676124508182204,
"max": 0.17213824540376663,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.477598840833334e-06,
"min": 3.477598840833334e-06,
"max": 0.000295303576565475,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0432796522500002e-05,
"min": 1.0432796522500002e-05,
"max": 0.0008439669186777,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115916666666669,
"min": 0.10115916666666669,
"max": 0.19843452500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347750000000007,
"min": 0.2074621000000001,
"max": 0.5813223000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.784241666666668e-05,
"min": 6.784241666666668e-05,
"max": 0.004921882797500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020352725000000004,
"min": 0.00020352725000000004,
"max": 0.014067982770000001,
"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": "1710764824",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710767480"
},
"total": 2656.669386874,
"count": 1,
"self": 0.8106683019996126,
"children": {
"run_training.setup": {
"total": 0.05793593499998906,
"count": 1,
"self": 0.05793593499998906
},
"TrainerController.start_learning": {
"total": 2655.8007826370003,
"count": 1,
"self": 5.087625308075076,
"children": {
"TrainerController._reset_env": {
"total": 3.5527164459999767,
"count": 1,
"self": 3.5527164459999767
},
"TrainerController.advance": {
"total": 2646.9746906309256,
"count": 232345,
"self": 5.232576097865149,
"children": {
"env_step": {
"total": 2142.96047657998,
"count": 232345,
"self": 1775.107775103956,
"children": {
"SubprocessEnvManager._take_step": {
"total": 364.47045951904835,
"count": 232345,
"self": 19.66540015796778,
"children": {
"TorchPolicy.evaluate": {
"total": 344.80505936108057,
"count": 222918,
"self": 344.80505936108057
}
}
},
"workers": {
"total": 3.3822419569755198,
"count": 232345,
"self": 0.0,
"children": {
"worker_root": {
"total": 2647.479681062063,
"count": 232345,
"is_parallel": true,
"self": 1216.7594174691585,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010156489999531004,
"count": 1,
"is_parallel": true,
"self": 0.00024872099999129205,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007669279999618084,
"count": 2,
"is_parallel": true,
"self": 0.0007669279999618084
}
}
},
"UnityEnvironment.step": {
"total": 0.03166987400004473,
"count": 1,
"is_parallel": true,
"self": 0.0004071999999837317,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023673499998722036,
"count": 1,
"is_parallel": true,
"self": 0.00023673499998722036
},
"communicator.exchange": {
"total": 0.030170979000047282,
"count": 1,
"is_parallel": true,
"self": 0.030170979000047282
},
"steps_from_proto": {
"total": 0.0008549600000264945,
"count": 1,
"is_parallel": true,
"self": 0.00022018900000375652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000634771000022738,
"count": 2,
"is_parallel": true,
"self": 0.000634771000022738
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1430.7202635929043,
"count": 232344,
"is_parallel": true,
"self": 42.763826085928486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.53034011201254,
"count": 232344,
"is_parallel": true,
"self": 93.53034011201254
},
"communicator.exchange": {
"total": 1191.7062954459493,
"count": 232344,
"is_parallel": true,
"self": 1191.7062954459493
},
"steps_from_proto": {
"total": 102.71980194901408,
"count": 232344,
"is_parallel": true,
"self": 38.544185027076765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.17561692193732,
"count": 464688,
"is_parallel": true,
"self": 64.17561692193732
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 498.7816379530806,
"count": 232345,
"self": 7.925342887081854,
"children": {
"process_trajectory": {
"total": 166.89708040700225,
"count": 232345,
"self": 165.37636776200202,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5207126450002306,
"count": 10,
"self": 1.5207126450002306
}
}
},
"_update_policy": {
"total": 323.9592146589965,
"count": 97,
"self": 259.96898862297843,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.99022603601804,
"count": 2910,
"self": 63.99022603601804
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4600000213249587e-06,
"count": 1,
"self": 1.4600000213249587e-06
},
"TrainerController._save_models": {
"total": 0.18574879199968564,
"count": 1,
"self": 0.0029095689997120644,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18283922299997357,
"count": 1,
"self": 0.18283922299997357
}
}
}
}
}
}
}