ppo-Huggy / run_logs /timers.json
aliakyurek's picture
Huggy
b91f9a5
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405135154724121,
"min": 1.405135154724121,
"max": 1.4280673265457153,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71851.5859375,
"min": 69454.5625,
"max": 76647.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.81072555205047,
"min": 73.57824143070044,
"max": 394.2992125984252,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49332.0,
"min": 49256.0,
"max": 50076.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49453.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49453.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4814648628234863,
"min": 0.0710405483841896,
"max": 2.4892094135284424,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1573.248779296875,
"min": 8.951108932495117,
"max": 1637.868896484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9001427038986978,
"min": 1.7934808780749638,
"max": 3.996470287594779,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2472.6904742717743,
"min": 225.97859063744545,
"max": 2593.1513600945473,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9001427038986978,
"min": 1.7934808780749638,
"max": 3.996470287594779,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2472.6904742717743,
"min": 225.97859063744545,
"max": 2593.1513600945473,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015761220289277844,
"min": 0.013570227298381117,
"max": 0.020041412301361562,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04728366086783353,
"min": 0.027140454596762235,
"max": 0.055974420600493124,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05431265934473938,
"min": 0.021707945317029954,
"max": 0.06779648972054322,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16293797803421814,
"min": 0.04341589063405991,
"max": 0.18679573809107144,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.743548752183338e-06,
"min": 3.743548752183338e-06,
"max": 0.000295304326565225,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1230646256550013e-05,
"min": 1.1230646256550013e-05,
"max": 0.0008440944186351997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012478166666667,
"min": 0.1012478166666667,
"max": 0.198434775,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037434500000001,
"min": 0.20764035000000003,
"max": 0.5813648000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.226605166666673e-05,
"min": 7.226605166666673e-05,
"max": 0.004921895272499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021679815500000017,
"min": 0.00021679815500000017,
"max": 0.014070103519999997,
"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": "1684339018",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684341377"
},
"total": 2359.703955216,
"count": 1,
"self": 0.7885307319997992,
"children": {
"run_training.setup": {
"total": 0.04133167899999535,
"count": 1,
"self": 0.04133167899999535
},
"TrainerController.start_learning": {
"total": 2358.874092805,
"count": 1,
"self": 4.359624597974289,
"children": {
"TrainerController._reset_env": {
"total": 4.074898700000006,
"count": 1,
"self": 4.074898700000006
},
"TrainerController.advance": {
"total": 2350.2663918440257,
"count": 233076,
"self": 4.59262590213757,
"children": {
"env_step": {
"total": 1825.3737059609125,
"count": 233076,
"self": 1540.6071812757775,
"children": {
"SubprocessEnvManager._take_step": {
"total": 281.9919693540062,
"count": 233076,
"self": 16.43427017608326,
"children": {
"TorchPolicy.evaluate": {
"total": 265.5576991779229,
"count": 222998,
"self": 265.5576991779229
}
}
},
"workers": {
"total": 2.7745553311288234,
"count": 233076,
"self": 0.0,
"children": {
"worker_root": {
"total": 2351.179177715009,
"count": 233076,
"is_parallel": true,
"self": 1093.4011141279675,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008870409999985895,
"count": 1,
"is_parallel": true,
"self": 0.0002638939999712875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006231470000273021,
"count": 2,
"is_parallel": true,
"self": 0.0006231470000273021
}
}
},
"UnityEnvironment.step": {
"total": 0.02942894900002102,
"count": 1,
"is_parallel": true,
"self": 0.00034135000001356275,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033636599999908867,
"count": 1,
"is_parallel": true,
"self": 0.00033636599999908867
},
"communicator.exchange": {
"total": 0.027983132999992222,
"count": 1,
"is_parallel": true,
"self": 0.027983132999992222
},
"steps_from_proto": {
"total": 0.0007681000000161475,
"count": 1,
"is_parallel": true,
"self": 0.00025058900001795337,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005175109999981942,
"count": 2,
"is_parallel": true,
"self": 0.0005175109999981942
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1257.7780635870413,
"count": 233075,
"is_parallel": true,
"self": 38.64761829694794,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.09318962095719,
"count": 233075,
"is_parallel": true,
"self": 77.09318962095719
},
"communicator.exchange": {
"total": 1049.7413828350896,
"count": 233075,
"is_parallel": true,
"self": 1049.7413828350896
},
"steps_from_proto": {
"total": 92.29587283404649,
"count": 233075,
"is_parallel": true,
"self": 33.70563547596032,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.59023735808617,
"count": 466150,
"is_parallel": true,
"self": 58.59023735808617
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 520.3000599809758,
"count": 233076,
"self": 6.422713615918042,
"children": {
"process_trajectory": {
"total": 135.7506579740562,
"count": 233076,
"self": 134.24002403705674,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5106339369994544,
"count": 10,
"self": 1.5106339369994544
}
}
},
"_update_policy": {
"total": 378.1266883910016,
"count": 97,
"self": 319.08928179400846,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.03740659699312,
"count": 2910,
"self": 59.03740659699312
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2609998520929366e-06,
"count": 1,
"self": 1.2609998520929366e-06
},
"TrainerController._save_models": {
"total": 0.173176402000081,
"count": 1,
"self": 0.0027945450001425343,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17038185699993846,
"count": 1,
"self": 0.17038185699993846
}
}
}
}
}
}
}