Alfredo Wijaya Hardjoprawiro
First Push
fc53e36
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3890590965747833,
"min": 0.3890590965747833,
"max": 1.4724088907241821,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11758.921875,
"min": 11758.921875,
"max": 44666.99609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989969.0,
"min": 29952.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989969.0,
"min": 29952.0,
"max": 989969.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3229532539844513,
"min": -0.13341304659843445,
"max": 0.3610764741897583,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 84.93670654296875,
"min": -31.618892669677734,
"max": 94.24095916748047,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.2123897522687912,
"min": -0.2123897522687912,
"max": 0.21322008967399597,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -55.85850524902344,
"min": -55.85850524902344,
"max": 51.59926223754883,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06856063251741164,
"min": 0.06531019518463298,
"max": 0.07870537492212241,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.959848855243763,
"min": 0.550937624454857,
"max": 1.0747200815161615,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01877180784595876,
"min": 0.0006723622541110371,
"max": 0.01877180784595876,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.26280530984342265,
"min": 0.008068347049332446,
"max": 0.26280530984342265,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.621490316678577e-06,
"min": 7.621490316678577e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010670086443350009,
"min": 0.00010670086443350009,
"max": 0.0035076878307708,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254046428571431,
"min": 0.10254046428571431,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355665000000004,
"min": 1.3886848,
"max": 2.5692292000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026379238214285734,
"min": 0.00026379238214285734,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003693093350000003,
"min": 0.003693093350000003,
"max": 0.11694599707999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009970290586352348,
"min": 0.009905577637255192,
"max": 0.3618645668029785,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13958406448364258,
"min": 0.13867808878421783,
"max": 2.5330519676208496,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 507.93333333333334,
"min": 507.93333333333334,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30476.0,
"min": 15984.0,
"max": 33306.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.392043303946654,
"min": -1.0000000521540642,
"max": 1.392043303946654,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 83.52259823679924,
"min": -30.371401749551296,
"max": 83.52259823679924,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.392043303946654,
"min": -1.0000000521540642,
"max": 1.392043303946654,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 83.52259823679924,
"min": -30.371401749551296,
"max": 83.52259823679924,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.053394688292367695,
"min": 0.053394688292367695,
"max": 7.051478681154549,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2036812975420617,
"min": 3.0953924180939794,
"max": 112.82365889847279,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1699716825",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699719298"
},
"total": 2472.689293259,
"count": 1,
"self": 0.8706576670001596,
"children": {
"run_training.setup": {
"total": 0.07064838399992368,
"count": 1,
"self": 0.07064838399992368
},
"TrainerController.start_learning": {
"total": 2471.747987208,
"count": 1,
"self": 1.5217242819981038,
"children": {
"TrainerController._reset_env": {
"total": 4.081776980999621,
"count": 1,
"self": 4.081776980999621
},
"TrainerController.advance": {
"total": 2466.025780588002,
"count": 63418,
"self": 1.5658055441435863,
"children": {
"env_step": {
"total": 1770.3805348169367,
"count": 63418,
"self": 1628.232818394927,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.22728737002717,
"count": 63418,
"self": 4.969750029818897,
"children": {
"TorchPolicy.evaluate": {
"total": 136.25753734020827,
"count": 62550,
"self": 136.25753734020827
}
}
},
"workers": {
"total": 0.9204290519824099,
"count": 63418,
"self": 0.0,
"children": {
"worker_root": {
"total": 2466.4065804200204,
"count": 63418,
"is_parallel": true,
"self": 971.7145316029628,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002979374000005919,
"count": 1,
"is_parallel": true,
"self": 0.0008370370001102856,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002142336999895633,
"count": 8,
"is_parallel": true,
"self": 0.002142336999895633
}
}
},
"UnityEnvironment.step": {
"total": 0.05552685700013171,
"count": 1,
"is_parallel": true,
"self": 0.00064110699986486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005579960002251028,
"count": 1,
"is_parallel": true,
"self": 0.0005579960002251028
},
"communicator.exchange": {
"total": 0.05248489699988568,
"count": 1,
"is_parallel": true,
"self": 0.05248489699988568
},
"steps_from_proto": {
"total": 0.001842857000156073,
"count": 1,
"is_parallel": true,
"self": 0.00039553599981445586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001447321000341617,
"count": 8,
"is_parallel": true,
"self": 0.001447321000341617
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1494.6920488170576,
"count": 63417,
"is_parallel": true,
"self": 36.35658904223237,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 27.17344772194383,
"count": 63417,
"is_parallel": true,
"self": 27.17344772194383
},
"communicator.exchange": {
"total": 1321.0606863620073,
"count": 63417,
"is_parallel": true,
"self": 1321.0606863620073
},
"steps_from_proto": {
"total": 110.10132569087409,
"count": 63417,
"is_parallel": true,
"self": 22.721931072894677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 87.37939461797941,
"count": 507336,
"is_parallel": true,
"self": 87.37939461797941
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 694.0794402269216,
"count": 63418,
"self": 2.702965976941414,
"children": {
"process_trajectory": {
"total": 137.97440756097694,
"count": 63418,
"self": 137.75985419097742,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21455336999952124,
"count": 2,
"self": 0.21455336999952124
}
}
},
"_update_policy": {
"total": 553.4020666890033,
"count": 452,
"self": 334.1396636349932,
"children": {
"TorchPPOOptimizer.update": {
"total": 219.26240305401006,
"count": 22767,
"self": 219.26240305401006
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3139997463440523e-06,
"count": 1,
"self": 1.3139997463440523e-06
},
"TrainerController._save_models": {
"total": 0.11870404300043447,
"count": 1,
"self": 0.001971915000467561,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1167321279999669,
"count": 1,
"self": 0.1167321279999669
}
}
}
}
}
}
}