chasleslrvr's picture
First Push
5621a03
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14443106949329376,
"min": 0.12395886331796646,
"max": 1.4736429452896118,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4376.83935546875,
"min": 3696.94921875,
"max": 44704.43359375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999951.0,
"min": 29952.0,
"max": 2999951.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999951.0,
"min": 29952.0,
"max": 2999951.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.759327232837677,
"min": -0.09899549931287766,
"max": 0.8721626400947571,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 226.27951049804688,
"min": -23.659923553466797,
"max": 266.88177490234375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0064148749224841595,
"min": -0.030041363090276718,
"max": 0.23260368406772614,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.911632776260376,
"min": -8.201292037963867,
"max": 56.05748748779297,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07115586713900686,
"min": 0.06428988575700575,
"max": 0.07526659736640427,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0673380070851028,
"min": 0.4893391144043102,
"max": 1.0937495368513432,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01591961610247381,
"min": 7.309240831982008e-05,
"max": 0.0178266942795938,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23879424153710715,
"min": 0.0009502013081576611,
"max": 0.25195073196322054,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.516346161251105e-06,
"min": 1.516346161251105e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2745192418766576e-05,
"min": 2.2745192418766576e-05,
"max": 0.004011129262956933,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050541555555557,
"min": 0.10050541555555557,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5075812333333336,
"min": 1.3962282666666668,
"max": 2.7370430666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.0491013999999816e-05,
"min": 6.0491013999999816e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0009073652099999972,
"min": 0.0009073652099999972,
"max": 0.13371060236,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0067823235876858234,
"min": 0.0067823235876858234,
"max": 0.4461281895637512,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10173485428094864,
"min": 0.09511439502239227,
"max": 3.1228973865509033,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 239.77235772357724,
"min": 207.7941176470588,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29492.0,
"min": 15984.0,
"max": 32892.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7439642217828006,
"min": -1.0000000521540642,
"max": 1.7920222146643532,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 214.50759927928448,
"min": -31.992401644587517,
"max": 241.9229989796877,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7439642217828006,
"min": -1.0000000521540642,
"max": 1.7920222146643532,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 214.50759927928448,
"min": -31.992401644587517,
"max": 241.9229989796877,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.016912048902342828,
"min": 0.014935455884464752,
"max": 8.944775504991412,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.080182014988168,
"min": 2.001351088518277,
"max": 143.1164080798626,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703176879",
"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/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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703184018"
},
"total": 7138.942009463999,
"count": 1,
"self": 0.4759285929976613,
"children": {
"run_training.setup": {
"total": 0.04950590500038743,
"count": 1,
"self": 0.04950590500038743
},
"TrainerController.start_learning": {
"total": 7138.416574966001,
"count": 1,
"self": 3.9906511059780314,
"children": {
"TrainerController._reset_env": {
"total": 2.1082676060000267,
"count": 1,
"self": 2.1082676060000267
},
"TrainerController.advance": {
"total": 7132.230837163023,
"count": 194987,
"self": 4.099471106595047,
"children": {
"env_step": {
"total": 5246.308607392738,
"count": 194987,
"self": 4873.28687172161,
"children": {
"SubprocessEnvManager._take_step": {
"total": 370.55495589813563,
"count": 194987,
"self": 13.496467821057195,
"children": {
"TorchPolicy.evaluate": {
"total": 357.05848807707844,
"count": 187571,
"self": 357.05848807707844
}
}
},
"workers": {
"total": 2.466779772992595,
"count": 194987,
"self": 0.0,
"children": {
"worker_root": {
"total": 7123.033331024346,
"count": 194987,
"is_parallel": true,
"self": 2602.2988787001723,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016946249997999985,
"count": 1,
"is_parallel": true,
"self": 0.0005256890003693115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001168935999430687,
"count": 8,
"is_parallel": true,
"self": 0.001168935999430687
}
}
},
"UnityEnvironment.step": {
"total": 0.049778992000028666,
"count": 1,
"is_parallel": true,
"self": 0.0006497639997178339,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000496684000154346,
"count": 1,
"is_parallel": true,
"self": 0.000496684000154346
},
"communicator.exchange": {
"total": 0.04689252900016072,
"count": 1,
"is_parallel": true,
"self": 0.04689252900016072
},
"steps_from_proto": {
"total": 0.0017400149999957648,
"count": 1,
"is_parallel": true,
"self": 0.00037818200053152395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013618329994642409,
"count": 8,
"is_parallel": true,
"self": 0.0013618329994642409
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4520.734452324174,
"count": 194986,
"is_parallel": true,
"self": 103.65027578090667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 71.20749580293796,
"count": 194986,
"is_parallel": true,
"self": 71.20749580293796
},
"communicator.exchange": {
"total": 4055.1857964828923,
"count": 194986,
"is_parallel": true,
"self": 4055.1857964828923
},
"steps_from_proto": {
"total": 290.6908842574371,
"count": 194986,
"is_parallel": true,
"self": 57.317195717796494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 233.37368853964063,
"count": 1559888,
"is_parallel": true,
"self": 233.37368853964063
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1881.82275866369,
"count": 194987,
"self": 8.240734182178585,
"children": {
"process_trajectory": {
"total": 384.27873121252424,
"count": 194987,
"self": 383.6423876325234,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6363435800008119,
"count": 6,
"self": 0.6363435800008119
}
}
},
"_update_policy": {
"total": 1489.303293268987,
"count": 1397,
"self": 884.9592297699401,
"children": {
"TorchPPOOptimizer.update": {
"total": 604.344063499047,
"count": 68397,
"self": 604.344063499047
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.507998604211025e-06,
"count": 1,
"self": 1.507998604211025e-06
},
"TrainerController._save_models": {
"total": 0.08681758300008369,
"count": 1,
"self": 0.0015036730001156684,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08531390999996802,
"count": 1,
"self": 0.08531390999996802
}
}
}
}
}
}
}