0x05a4's picture
Huggy baseline
e81add4
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4029122591018677,
"min": 1.4029122591018677,
"max": 1.4289779663085938,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69345.953125,
"min": 69057.75,
"max": 77257.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.5392749244713,
"min": 68.80753138075313,
"max": 397.73809523809524,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49345.0,
"min": 48659.0,
"max": 50115.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999935.0,
"min": 49852.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999935.0,
"min": 49852.0,
"max": 1999935.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5473945140838623,
"min": 0.04203926399350166,
"max": 2.550143003463745,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1686.3751220703125,
"min": 5.254908084869385,
"max": 1762.5511474609375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8851647268969485,
"min": 1.7560807373523712,
"max": 4.001453762911013,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2571.97904920578,
"min": 219.5100921690464,
"max": 2745.775563776493,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8851647268969485,
"min": 1.7560807373523712,
"max": 4.001453762911013,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2571.97904920578,
"min": 219.5100921690464,
"max": 2745.775563776493,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01593627496816528,
"min": 0.01445691912570813,
"max": 0.021267814645155644,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047808824904495846,
"min": 0.029374661512944537,
"max": 0.05762480510287181,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06602705303165647,
"min": 0.022622768549869457,
"max": 0.06626627705991268,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19808115909496943,
"min": 0.045245537099738914,
"max": 0.19808115909496943,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6432987856000026e-06,
"min": 3.6432987856000026e-06,
"max": 0.00029532187655937497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0929896356800007e-05,
"min": 1.0929896356800007e-05,
"max": 0.0008442109685963498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121440000000002,
"min": 0.10121440000000002,
"max": 0.19844062500000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30364320000000006,
"min": 0.20762260000000005,
"max": 0.58140365,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.059856000000006e-05,
"min": 7.059856000000006e-05,
"max": 0.0049221871875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021179568000000018,
"min": 0.00021179568000000018,
"max": 0.014072042134999999,
"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": "1687976470",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1687978842"
},
"total": 2372.567183867,
"count": 1,
"self": 0.44377431099974274,
"children": {
"run_training.setup": {
"total": 0.052851534000012634,
"count": 1,
"self": 0.052851534000012634
},
"TrainerController.start_learning": {
"total": 2372.070558022,
"count": 1,
"self": 4.136896917132162,
"children": {
"TrainerController._reset_env": {
"total": 5.02452770299999,
"count": 1,
"self": 5.02452770299999
},
"TrainerController.advance": {
"total": 2362.7916916778686,
"count": 233739,
"self": 4.399068805028037,
"children": {
"env_step": {
"total": 1834.8994433758926,
"count": 233739,
"self": 1549.271172808939,
"children": {
"SubprocessEnvManager._take_step": {
"total": 282.9626284670042,
"count": 233739,
"self": 16.125975865004932,
"children": {
"TorchPolicy.evaluate": {
"total": 266.8366526019993,
"count": 222918,
"self": 266.8366526019993
}
}
},
"workers": {
"total": 2.6656420999495367,
"count": 233739,
"self": 0.0,
"children": {
"worker_root": {
"total": 2364.514131559955,
"count": 233739,
"is_parallel": true,
"self": 1100.7878723188514,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011334609999948952,
"count": 1,
"is_parallel": true,
"self": 0.000324948999946173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008085120000487223,
"count": 2,
"is_parallel": true,
"self": 0.0008085120000487223
}
}
},
"UnityEnvironment.step": {
"total": 0.04142993400000705,
"count": 1,
"is_parallel": true,
"self": 0.0004121910000662865,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023317099999076163,
"count": 1,
"is_parallel": true,
"self": 0.00023317099999076163
},
"communicator.exchange": {
"total": 0.04007274800000005,
"count": 1,
"is_parallel": true,
"self": 0.04007274800000005
},
"steps_from_proto": {
"total": 0.0007118239999499565,
"count": 1,
"is_parallel": true,
"self": 0.00019454299996368718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005172809999862693,
"count": 2,
"is_parallel": true,
"self": 0.0005172809999862693
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.7262592411034,
"count": 233738,
"is_parallel": true,
"self": 38.86115494229625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.81810240694153,
"count": 233738,
"is_parallel": true,
"self": 77.81810240694153
},
"communicator.exchange": {
"total": 1053.264788479931,
"count": 233738,
"is_parallel": true,
"self": 1053.264788479931
},
"steps_from_proto": {
"total": 93.78221341193466,
"count": 233738,
"is_parallel": true,
"self": 33.44287346898341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.339339942951256,
"count": 467476,
"is_parallel": true,
"self": 60.339339942951256
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 523.4931794969481,
"count": 233739,
"self": 6.474948635922374,
"children": {
"process_trajectory": {
"total": 140.9267903490267,
"count": 233739,
"self": 139.50666935202622,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4201209970004811,
"count": 10,
"self": 1.4201209970004811
}
}
},
"_update_policy": {
"total": 376.091440511999,
"count": 97,
"self": 316.08709180000017,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.00434871199883,
"count": 2910,
"self": 60.00434871199883
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.321999661740847e-06,
"count": 1,
"self": 1.321999661740847e-06
},
"TrainerController._save_models": {
"total": 0.11744040199982919,
"count": 1,
"self": 0.0018822739998540783,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11555812799997511,
"count": 1,
"self": 0.11555812799997511
}
}
}
}
}
}
}