ppo-Huggy / run_logs /timers.json
SjcCss's picture
Huggy
2934154 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4093338251113892,
"min": 1.4093338251113892,
"max": 1.4316974878311157,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70153.8203125,
"min": 68282.75,
"max": 77714.3671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.46911196911196,
"min": 91.04066543438077,
"max": 417.525,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49453.0,
"min": 48930.0,
"max": 50284.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999943.0,
"min": 49996.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999943.0,
"min": 49996.0,
"max": 1999943.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.387260675430298,
"min": 0.10630378127098083,
"max": 2.387260675430298,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1236.60107421875,
"min": 12.650150299072266,
"max": 1265.12890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8618637688141533,
"min": 1.8359835165388443,
"max": 3.8618637688141533,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2000.4454322457314,
"min": 218.48203846812248,
"max": 2038.8616166710854,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8618637688141533,
"min": 1.8359835165388443,
"max": 3.8618637688141533,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2000.4454322457314,
"min": 218.48203846812248,
"max": 2038.8616166710854,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016457050095454583,
"min": 0.013975098124097307,
"max": 0.020175672068338223,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04937115028636375,
"min": 0.028371219928279363,
"max": 0.057719306598301046,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050252181291580204,
"min": 0.020378964580595495,
"max": 0.06624384319616688,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1507565438747406,
"min": 0.04075792916119099,
"max": 0.19873152958850065,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1784489405499967e-06,
"min": 3.1784489405499967e-06,
"max": 0.00029531175156274995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.53534682164999e-06,
"min": 9.53534682164999e-06,
"max": 0.0008440536186487999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105944999999998,
"min": 0.10105944999999998,
"max": 0.19843725,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30317834999999993,
"min": 0.20727679999999998,
"max": 0.5813512000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.286655499999995e-05,
"min": 6.286655499999995e-05,
"max": 0.004922018775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018859966499999988,
"min": 0.00018859966499999988,
"max": 0.014069424879999997,
"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": "1757678965",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1757681411"
},
"total": 2445.945887228,
"count": 1,
"self": 0.4368705500000942,
"children": {
"run_training.setup": {
"total": 0.024801733000003878,
"count": 1,
"self": 0.024801733000003878
},
"TrainerController.start_learning": {
"total": 2445.484214945,
"count": 1,
"self": 4.21893454209885,
"children": {
"TrainerController._reset_env": {
"total": 2.8453478090000317,
"count": 1,
"self": 2.8453478090000317
},
"TrainerController.advance": {
"total": 2438.317320932901,
"count": 231212,
"self": 4.368276426931061,
"children": {
"env_step": {
"total": 1963.0049337879682,
"count": 231212,
"self": 1555.5160855859508,
"children": {
"SubprocessEnvManager._take_step": {
"total": 404.73353135705736,
"count": 231212,
"self": 15.757463924952162,
"children": {
"TorchPolicy.evaluate": {
"total": 388.9760674321052,
"count": 222874,
"self": 388.9760674321052
}
}
},
"workers": {
"total": 2.755316844959907,
"count": 231212,
"self": 0.0,
"children": {
"worker_root": {
"total": 2437.962043447956,
"count": 231212,
"is_parallel": true,
"self": 1169.4765717980122,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008905199999844626,
"count": 1,
"is_parallel": true,
"self": 0.00024371799997879862,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000646802000005664,
"count": 2,
"is_parallel": true,
"self": 0.000646802000005664
}
}
},
"UnityEnvironment.step": {
"total": 0.029645762999962244,
"count": 1,
"is_parallel": true,
"self": 0.00032959400016352447,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001888569998982348,
"count": 1,
"is_parallel": true,
"self": 0.0001888569998982348
},
"communicator.exchange": {
"total": 0.028418947999966804,
"count": 1,
"is_parallel": true,
"self": 0.028418947999966804
},
"steps_from_proto": {
"total": 0.000708363999933681,
"count": 1,
"is_parallel": true,
"self": 0.00019807199998922442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005102919999444566,
"count": 2,
"is_parallel": true,
"self": 0.0005102919999444566
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1268.485471649944,
"count": 231211,
"is_parallel": true,
"self": 36.98203932387378,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.28399110700445,
"count": 231211,
"is_parallel": true,
"self": 82.28399110700445
},
"communicator.exchange": {
"total": 1060.3577640710623,
"count": 231211,
"is_parallel": true,
"self": 1060.3577640710623
},
"steps_from_proto": {
"total": 88.8616771480032,
"count": 231211,
"is_parallel": true,
"self": 32.76879915195559,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.092877996047605,
"count": 462422,
"is_parallel": true,
"self": 56.092877996047605
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 470.94411071800175,
"count": 231212,
"self": 6.376484194020463,
"children": {
"process_trajectory": {
"total": 148.35440709397938,
"count": 231212,
"self": 147.08381053897972,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2705965549996563,
"count": 10,
"self": 1.2705965549996563
}
}
},
"_update_policy": {
"total": 316.2132194300019,
"count": 97,
"self": 252.3457105460093,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.86750888399263,
"count": 2910,
"self": 63.86750888399263
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.789997991698328e-07,
"count": 1,
"self": 8.789997991698328e-07
},
"TrainerController._save_models": {
"total": 0.1026107820002835,
"count": 1,
"self": 0.002602287000627257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10000849499965625,
"count": 1,
"self": 0.10000849499965625
}
}
}
}
}
}
}