ppo-Huggy / run_logs /timers.json
benedikt-schaber's picture
initial model commit
c58500c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.410426139831543,
"min": 1.4104138612747192,
"max": 1.4326211214065552,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72397.171875,
"min": 68567.75,
"max": 76220.90625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.90268456375838,
"min": 78.76874003189792,
"max": 393.62204724409446,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49410.0,
"min": 49089.0,
"max": 50230.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999895.0,
"min": 49756.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999895.0,
"min": 49756.0,
"max": 1999895.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4811394214630127,
"min": 0.2155127376317978,
"max": 2.493774175643921,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1478.7591552734375,
"min": 27.154605865478516,
"max": 1504.406005859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.897431251386668,
"min": 1.919112698899375,
"max": 3.971654632074762,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2322.869025826454,
"min": 241.80820006132126,
"max": 2355.90917044878,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.897431251386668,
"min": 1.919112698899375,
"max": 3.971654632074762,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2322.869025826454,
"min": 241.80820006132126,
"max": 2355.90917044878,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014041133376061528,
"min": 0.013165216731431428,
"max": 0.02166821646023891,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.042123400128184586,
"min": 0.026330433462862856,
"max": 0.05489225556302699,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06239319741725922,
"min": 0.019758328578124443,
"max": 0.07129623542229335,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18717959225177766,
"min": 0.039516657156248886,
"max": 0.20020251733561356,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5204988265333345e-06,
"min": 3.5204988265333345e-06,
"max": 0.000295370626543125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0561496479600003e-05,
"min": 1.0561496479600003e-05,
"max": 0.0008442045185985,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117346666666667,
"min": 0.10117346666666667,
"max": 0.19845687500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035204,
"min": 0.20750905000000003,
"max": 0.5814015000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.855598666666671e-05,
"min": 6.855598666666671e-05,
"max": 0.0049229980625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020566796000000016,
"min": 0.00020566796000000016,
"max": 0.01407193485,
"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": "1695310665",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1695313193"
},
"total": 2528.1297736459996,
"count": 1,
"self": 0.4403649459995904,
"children": {
"run_training.setup": {
"total": 0.07032263999997213,
"count": 1,
"self": 0.07032263999997213
},
"TrainerController.start_learning": {
"total": 2527.61908606,
"count": 1,
"self": 4.780871037948145,
"children": {
"TrainerController._reset_env": {
"total": 4.615533321999919,
"count": 1,
"self": 4.615533321999919
},
"TrainerController.advance": {
"total": 2518.092652988052,
"count": 232088,
"self": 4.556559317105894,
"children": {
"env_step": {
"total": 1941.700954344933,
"count": 232088,
"self": 1642.2340080639601,
"children": {
"SubprocessEnvManager._take_step": {
"total": 296.45185744504727,
"count": 232088,
"self": 17.167045341020184,
"children": {
"TorchPolicy.evaluate": {
"total": 279.2848121040271,
"count": 222984,
"self": 279.2848121040271
}
}
},
"workers": {
"total": 3.015088835925553,
"count": 232088,
"self": 0.0,
"children": {
"worker_root": {
"total": 2519.776367516043,
"count": 232088,
"is_parallel": true,
"self": 1176.5351518609914,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013956999999891195,
"count": 1,
"is_parallel": true,
"self": 0.00039126399985889293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010044360001302266,
"count": 2,
"is_parallel": true,
"self": 0.0010044360001302266
}
}
},
"UnityEnvironment.step": {
"total": 0.030746516000021984,
"count": 1,
"is_parallel": true,
"self": 0.00035151899999164016,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021772700006295054,
"count": 1,
"is_parallel": true,
"self": 0.00021772700006295054
},
"communicator.exchange": {
"total": 0.029355240999962007,
"count": 1,
"is_parallel": true,
"self": 0.029355240999962007
},
"steps_from_proto": {
"total": 0.0008220290000053865,
"count": 1,
"is_parallel": true,
"self": 0.00024365399997350323,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005783750000318832,
"count": 2,
"is_parallel": true,
"self": 0.0005783750000318832
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1343.2412156550517,
"count": 232087,
"is_parallel": true,
"self": 41.587925768144714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.57488639197925,
"count": 232087,
"is_parallel": true,
"self": 82.57488639197925
},
"communicator.exchange": {
"total": 1117.0851646429523,
"count": 232087,
"is_parallel": true,
"self": 1117.0851646429523
},
"steps_from_proto": {
"total": 101.99323885197532,
"count": 232087,
"is_parallel": true,
"self": 36.21880443589805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.77443441607727,
"count": 464174,
"is_parallel": true,
"self": 65.77443441607727
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 571.8351393260133,
"count": 232088,
"self": 6.820293211021976,
"children": {
"process_trajectory": {
"total": 140.04120620198967,
"count": 232088,
"self": 138.6284720989895,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4127341030001617,
"count": 10,
"self": 1.4127341030001617
}
}
},
"_update_policy": {
"total": 424.97363991300165,
"count": 97,
"self": 363.26996284601057,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.70367706699108,
"count": 2910,
"self": 61.70367706699108
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3349999790079892e-06,
"count": 1,
"self": 1.3349999790079892e-06
},
"TrainerController._save_models": {
"total": 0.1300273769998057,
"count": 1,
"self": 0.001920495999911509,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1281068809998942,
"count": 1,
"self": 0.1281068809998942
}
}
}
}
}
}
}