ppo-Huggy / run_logs /timers.json
danceone's picture
Huggy
34a85c5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4054033756256104,
"min": 1.4054033756256104,
"max": 1.4263839721679688,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70943.359375,
"min": 68863.046875,
"max": 77082.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.63431542461005,
"min": 80.84364820846906,
"max": 386.86046511627904,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49988.0,
"min": 48766.0,
"max": 50267.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999860.0,
"min": 49588.0,
"max": 1999860.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999860.0,
"min": 49588.0,
"max": 1999860.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4407742023468018,
"min": 0.018891561776399612,
"max": 2.511622667312622,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1408.32666015625,
"min": 2.4181199073791504,
"max": 1488.81787109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7168054583787504,
"min": 1.8055895175784826,
"max": 3.988239465084943,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2144.596749484539,
"min": 231.11545825004578,
"max": 2335.0678215026855,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7168054583787504,
"min": 1.8055895175784826,
"max": 3.988239465084943,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2144.596749484539,
"min": 231.11545825004578,
"max": 2335.0678215026855,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016929692113545673,
"min": 0.013867745110312373,
"max": 0.019149900773966996,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050789076340637014,
"min": 0.027918123567421085,
"max": 0.05744970232190098,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.059997799247503286,
"min": 0.02217316438133518,
"max": 0.06565437478323777,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17999339774250986,
"min": 0.04434632876267036,
"max": 0.18991369480888048,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6014987995333323e-06,
"min": 3.6014987995333323e-06,
"max": 0.000295297876567375,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0804496398599997e-05,
"min": 1.0804496398599997e-05,
"max": 0.0008439807186731,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012004666666667,
"min": 0.1012004666666667,
"max": 0.19843262499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036014000000001,
"min": 0.20755115000000002,
"max": 0.5813269,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.990328666666667e-05,
"min": 6.990328666666667e-05,
"max": 0.0049217879875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020970985999999999,
"min": 0.00020970985999999999,
"max": 0.014068212310000001,
"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": "1753635201",
"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=Huggy --no-graphics",
"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": "1753637719"
},
"total": 2517.853427614,
"count": 1,
"self": 0.446255229000144,
"children": {
"run_training.setup": {
"total": 0.022954744000003302,
"count": 1,
"self": 0.022954744000003302
},
"TrainerController.start_learning": {
"total": 2517.384217641,
"count": 1,
"self": 4.452391938115397,
"children": {
"TrainerController._reset_env": {
"total": 3.1021159060001082,
"count": 1,
"self": 3.1021159060001082
},
"TrainerController.advance": {
"total": 2509.7213823648844,
"count": 232499,
"self": 4.629806240770449,
"children": {
"env_step": {
"total": 2030.2261629940508,
"count": 232499,
"self": 1603.7055552759516,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.7002508280326,
"count": 232499,
"self": 16.318884168068962,
"children": {
"TorchPolicy.evaluate": {
"total": 407.38136665996365,
"count": 222943,
"self": 407.38136665996365
}
}
},
"workers": {
"total": 2.8203568900665914,
"count": 232499,
"self": 0.0,
"children": {
"worker_root": {
"total": 2509.8528867150835,
"count": 232499,
"is_parallel": true,
"self": 1204.7492034710717,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009554309999657562,
"count": 1,
"is_parallel": true,
"self": 0.0002526660000512493,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007027649999145069,
"count": 2,
"is_parallel": true,
"self": 0.0007027649999145069
}
}
},
"UnityEnvironment.step": {
"total": 0.030510561000028247,
"count": 1,
"is_parallel": true,
"self": 0.000348859000041557,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020376999998461542,
"count": 1,
"is_parallel": true,
"self": 0.00020376999998461542
},
"communicator.exchange": {
"total": 0.02921463199993468,
"count": 1,
"is_parallel": true,
"self": 0.02921463199993468
},
"steps_from_proto": {
"total": 0.0007433000000673928,
"count": 1,
"is_parallel": true,
"self": 0.0002050480001116739,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005382519999557189,
"count": 2,
"is_parallel": true,
"self": 0.0005382519999557189
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1305.1036832440118,
"count": 232498,
"is_parallel": true,
"self": 37.914473654203675,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.23172151894846,
"count": 232498,
"is_parallel": true,
"self": 84.23172151894846
},
"communicator.exchange": {
"total": 1091.9515895399054,
"count": 232498,
"is_parallel": true,
"self": 1091.9515895399054
},
"steps_from_proto": {
"total": 91.00589853095425,
"count": 232498,
"is_parallel": true,
"self": 34.20654718900232,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.79935134195193,
"count": 464996,
"is_parallel": true,
"self": 56.79935134195193
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 474.8654131300632,
"count": 232499,
"self": 6.8999502540075355,
"children": {
"process_trajectory": {
"total": 169.54967833105786,
"count": 232499,
"self": 168.29316661905887,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2565117119989964,
"count": 10,
"self": 1.2565117119989964
}
}
},
"_update_policy": {
"total": 298.4157845449978,
"count": 97,
"self": 236.7312826400032,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.68450190499459,
"count": 2910,
"self": 61.68450190499459
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.369997885893099e-07,
"count": 1,
"self": 8.369997885893099e-07
},
"TrainerController._save_models": {
"total": 0.10832659500010777,
"count": 1,
"self": 0.0015905870004644385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10673600799964333,
"count": 1,
"self": 0.10673600799964333
}
}
}
}
}
}
}