tonio0192's picture
Huggy
69b9b7e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40896737575531,
"min": 1.40896737575531,
"max": 1.425002098083496,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72295.5234375,
"min": 67584.015625,
"max": 78683.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.34078212290503,
"min": 81.94019933554817,
"max": 389.015503875969,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50124.0,
"min": 49328.0,
"max": 50183.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999929.0,
"min": 49708.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999929.0,
"min": 49708.0,
"max": 1999929.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3812966346740723,
"min": -0.032368168234825134,
"max": 2.4586973190307617,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1278.75634765625,
"min": -4.143125534057617,
"max": 1430.9617919921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.663728304637433,
"min": 1.7387429201044142,
"max": 3.9482965452974197,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1967.4220995903015,
"min": 222.55909377336502,
"max": 2297.908589363098,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.663728304637433,
"min": 1.7387429201044142,
"max": 3.9482965452974197,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1967.4220995903015,
"min": 222.55909377336502,
"max": 2297.908589363098,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019278681794268476,
"min": 0.013200291108417634,
"max": 0.022318733865055645,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05783604538280543,
"min": 0.028128173277703658,
"max": 0.05783604538280543,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054327927902340895,
"min": 0.024612176511436698,
"max": 0.0553683360831605,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16298378370702268,
"min": 0.049224353022873396,
"max": 0.16610500824948152,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6591487803166745e-06,
"min": 3.6591487803166745e-06,
"max": 0.00029538157653947496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0977446340950023e-05,
"min": 1.0977446340950023e-05,
"max": 0.00084433906855365,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121968333333332,
"min": 0.10121968333333332,
"max": 0.19846052500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365905,
"min": 0.20758775000000002,
"max": 0.5814463500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.08621983333335e-05,
"min": 7.08621983333335e-05,
"max": 0.0049231801975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021258659500000048,
"min": 0.00021258659500000048,
"max": 0.014074172865,
"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": "1717515571",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717518107"
},
"total": 2536.283662894,
"count": 1,
"self": 0.43940012700022635,
"children": {
"run_training.setup": {
"total": 0.05761656999999332,
"count": 1,
"self": 0.05761656999999332
},
"TrainerController.start_learning": {
"total": 2535.7866461969998,
"count": 1,
"self": 4.514495969023301,
"children": {
"TrainerController._reset_env": {
"total": 2.958520944999975,
"count": 1,
"self": 2.958520944999975
},
"TrainerController.advance": {
"total": 2528.1959709309763,
"count": 232300,
"self": 4.804421871010618,
"children": {
"env_step": {
"total": 1997.992325272999,
"count": 232300,
"self": 1650.2422206760498,
"children": {
"SubprocessEnvManager._take_step": {
"total": 344.70062416501395,
"count": 232300,
"self": 17.863698769939674,
"children": {
"TorchPolicy.evaluate": {
"total": 326.8369253950743,
"count": 223089,
"self": 326.8369253950743
}
}
},
"workers": {
"total": 3.0494804319353648,
"count": 232300,
"self": 0.0,
"children": {
"worker_root": {
"total": 2528.237546674062,
"count": 232300,
"is_parallel": true,
"self": 1199.569869588998,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00093011500001694,
"count": 1,
"is_parallel": true,
"self": 0.0002531060000023899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006770090000145501,
"count": 2,
"is_parallel": true,
"self": 0.0006770090000145501
}
}
},
"UnityEnvironment.step": {
"total": 0.030904184999997142,
"count": 1,
"is_parallel": true,
"self": 0.00038646999996672093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020062200002257669,
"count": 1,
"is_parallel": true,
"self": 0.00020062200002257669
},
"communicator.exchange": {
"total": 0.029568003000008503,
"count": 1,
"is_parallel": true,
"self": 0.029568003000008503
},
"steps_from_proto": {
"total": 0.0007490899999993417,
"count": 1,
"is_parallel": true,
"self": 0.00019744400003673945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005516459999626022,
"count": 2,
"is_parallel": true,
"self": 0.0005516459999626022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1328.6676770850638,
"count": 232299,
"is_parallel": true,
"self": 39.92620387707257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.74713919600043,
"count": 232299,
"is_parallel": true,
"self": 86.74713919600043
},
"communicator.exchange": {
"total": 1107.8097907319532,
"count": 232299,
"is_parallel": true,
"self": 1107.8097907319532
},
"steps_from_proto": {
"total": 94.18454328003753,
"count": 232299,
"is_parallel": true,
"self": 35.869946047996166,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.314597232041365,
"count": 464598,
"is_parallel": true,
"self": 58.314597232041365
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 525.3992237869668,
"count": 232300,
"self": 6.809404869985315,
"children": {
"process_trajectory": {
"total": 161.2129844339816,
"count": 232300,
"self": 159.77276063598237,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4402237979992378,
"count": 10,
"self": 1.4402237979992378
}
}
},
"_update_policy": {
"total": 357.37683448299987,
"count": 97,
"self": 291.3815446019939,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.99528988100599,
"count": 2910,
"self": 65.99528988100599
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.88000010693213e-07,
"count": 1,
"self": 9.88000010693213e-07
},
"TrainerController._save_models": {
"total": 0.11765736400002424,
"count": 1,
"self": 0.002508828000372887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11514853599965136,
"count": 1,
"self": 0.11514853599965136
}
}
}
}
}
}
}