ppo-Huggy / run_logs /timers.json
raj777's picture
Huggy initial
c3c1df8 verified
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4057735204696655,
"min": 1.4057735204696655,
"max": 1.4285060167312622,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72712.2265625,
"min": 68265.796875,
"max": 77670.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.2294776119403,
"min": 74.96960486322189,
"max": 379.3560606060606,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49435.0,
"min": 48733.0,
"max": 50114.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999906.0,
"min": 49740.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999906.0,
"min": 49740.0,
"max": 1999906.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4367098808288574,
"min": -0.022639401257038116,
"max": 2.4571714401245117,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1306.0765380859375,
"min": -2.965761661529541,
"max": 1611.904541015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7937595180388706,
"min": 1.5887558141737494,
"max": 4.017628934288822,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2033.4551016688347,
"min": 208.12701165676117,
"max": 2586.200783252716,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7937595180388706,
"min": 1.5887558141737494,
"max": 4.017628934288822,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2033.4551016688347,
"min": 208.12701165676117,
"max": 2586.200783252716,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015258237045216243,
"min": 0.013167330232681707,
"max": 0.01907403057848569,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04577471113564873,
"min": 0.026334660465363414,
"max": 0.05567014217182683,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04590169390042623,
"min": 0.02249756644790371,
"max": 0.060108517793317634,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13770508170127868,
"min": 0.04499513289580742,
"max": 0.17758767120540142,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.481598839499992e-06,
"min": 3.481598839499992e-06,
"max": 0.00029531745156084993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0444796518499976e-05,
"min": 1.0444796518499976e-05,
"max": 0.0008437959187347,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116050000000003,
"min": 0.10116050000000003,
"max": 0.19843915,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348150000000007,
"min": 0.2074775000000001,
"max": 0.5812653000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.790894999999989e-05,
"min": 6.790894999999989e-05,
"max": 0.0049221135849999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020372684999999966,
"min": 0.00020372684999999966,
"max": 0.014065138470000006,
"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": "1727584113",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727586488"
},
"total": 2375.4458150540004,
"count": 1,
"self": 0.4369483320006111,
"children": {
"run_training.setup": {
"total": 0.0575439379999807,
"count": 1,
"self": 0.0575439379999807
},
"TrainerController.start_learning": {
"total": 2374.951322784,
"count": 1,
"self": 4.334001932152205,
"children": {
"TrainerController._reset_env": {
"total": 2.784236225000086,
"count": 1,
"self": 2.784236225000086
},
"TrainerController.advance": {
"total": 2367.725893388848,
"count": 232970,
"self": 4.527190872761821,
"children": {
"env_step": {
"total": 1874.547871341013,
"count": 232970,
"self": 1484.9540040981171,
"children": {
"SubprocessEnvManager._take_step": {
"total": 386.9792457520225,
"count": 232970,
"self": 15.020139462952784,
"children": {
"TorchPolicy.evaluate": {
"total": 371.9591062890697,
"count": 223086,
"self": 371.9591062890697
}
}
},
"workers": {
"total": 2.6146214908733327,
"count": 232970,
"self": 0.0,
"children": {
"worker_root": {
"total": 2367.581723784115,
"count": 232970,
"is_parallel": true,
"self": 1162.2689349780865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009651569998823106,
"count": 1,
"is_parallel": true,
"self": 0.0002776199999061646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000687536999976146,
"count": 2,
"is_parallel": true,
"self": 0.000687536999976146
}
}
},
"UnityEnvironment.step": {
"total": 0.028484001999913744,
"count": 1,
"is_parallel": true,
"self": 0.0003489150001314556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019967000002907298,
"count": 1,
"is_parallel": true,
"self": 0.00019967000002907298
},
"communicator.exchange": {
"total": 0.02719683299983444,
"count": 1,
"is_parallel": true,
"self": 0.02719683299983444
},
"steps_from_proto": {
"total": 0.0007385839999187738,
"count": 1,
"is_parallel": true,
"self": 0.00019069899985879601,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005478850000599778,
"count": 2,
"is_parallel": true,
"self": 0.0005478850000599778
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1205.3127888060287,
"count": 232969,
"is_parallel": true,
"self": 36.744132045027754,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.73818172201027,
"count": 232969,
"is_parallel": true,
"self": 78.73818172201027
},
"communicator.exchange": {
"total": 1004.3485599450685,
"count": 232969,
"is_parallel": true,
"self": 1004.3485599450685
},
"steps_from_proto": {
"total": 85.48191509392223,
"count": 232969,
"is_parallel": true,
"self": 30.343019061139557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.13889603278267,
"count": 465938,
"is_parallel": true,
"self": 55.13889603278267
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 488.6508311750731,
"count": 232970,
"self": 6.093957173114404,
"children": {
"process_trajectory": {
"total": 157.81097217095976,
"count": 232970,
"self": 156.37510409395964,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4358680770001229,
"count": 10,
"self": 1.4358680770001229
}
}
},
"_update_policy": {
"total": 324.74590183099895,
"count": 97,
"self": 260.34143709598334,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.40446473501561,
"count": 2910,
"self": 64.40446473501561
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1849997463286854e-06,
"count": 1,
"self": 1.1849997463286854e-06
},
"TrainerController._save_models": {
"total": 0.10719005299961282,
"count": 1,
"self": 0.0017946589996427065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10539539399997011,
"count": 1,
"self": 0.10539539399997011
}
}
}
}
}
}
}