G-e-o-r-g-e's picture
First Push
10035e4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3974633514881134,
"min": 0.3974633514881134,
"max": 1.3860630989074707,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11828.509765625,
"min": 11828.509765625,
"max": 42047.609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989926.0,
"min": 29963.0,
"max": 989926.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989926.0,
"min": 29963.0,
"max": 989926.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5517375469207764,
"min": -0.2758840024471283,
"max": 0.5802815556526184,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 151.17608642578125,
"min": -65.66039276123047,
"max": 162.4788360595703,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.059440989047288895,
"min": -0.059440989047288895,
"max": 0.35562530159950256,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -16.28683090209961,
"min": -16.28683090209961,
"max": 84.63882446289062,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06907752551422972,
"min": 0.06543076767550139,
"max": 0.07360878393833825,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0361628827134457,
"min": 0.47618490391298485,
"max": 1.088185845905066,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014112217849793118,
"min": 0.0002013832683728059,
"max": 0.018784578766263577,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21168326774689677,
"min": 0.002617982488846477,
"max": 0.26298410272769007,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5210974930000025e-06,
"min": 7.5210974930000025e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011281646239500004,
"min": 0.00011281646239500004,
"max": 0.0035080310306564,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250700000000003,
"min": 0.10250700000000003,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376050000000003,
"min": 1.3886848,
"max": 2.5693436000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002604493000000001,
"min": 0.0002604493000000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003906739500000002,
"min": 0.003906739500000002,
"max": 0.11695742563999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009851681999862194,
"min": 0.009851681999862194,
"max": 0.31373777985572815,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14777523279190063,
"min": 0.14002740383148193,
"max": 2.19616436958313,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 336.66265060240966,
"min": 315.5980392156863,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27943.0,
"min": 17657.0,
"max": 32191.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6151373336114079,
"min": -0.9999500527046621,
"max": 1.6451744925157696,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 134.05639868974686,
"min": -31.998401686549187,
"max": 167.8077982366085,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6151373336114079,
"min": -0.9999500527046621,
"max": 1.6451744925157696,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 134.05639868974686,
"min": -31.998401686549187,
"max": 167.8077982366085,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.034749603486642335,
"min": 0.03265691085877787,
"max": 6.357669523606698,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8842170893913135,
"min": 2.8842170893913135,
"max": 114.43805142492056,
"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": "1677061127",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1677063369"
},
"total": 2241.6221839629998,
"count": 1,
"self": 0.4943588629998885,
"children": {
"run_training.setup": {
"total": 0.1096670239999753,
"count": 1,
"self": 0.1096670239999753
},
"TrainerController.start_learning": {
"total": 2241.018158076,
"count": 1,
"self": 1.265138855969326,
"children": {
"TrainerController._reset_env": {
"total": 11.310362534999967,
"count": 1,
"self": 11.310362534999967
},
"TrainerController.advance": {
"total": 2228.356888022031,
"count": 63763,
"self": 1.4005332160950275,
"children": {
"env_step": {
"total": 1482.91388113997,
"count": 63763,
"self": 1371.289956186916,
"children": {
"SubprocessEnvManager._take_step": {
"total": 110.8391440770111,
"count": 63763,
"self": 4.643701398978692,
"children": {
"TorchPolicy.evaluate": {
"total": 106.1954426780324,
"count": 62553,
"self": 35.86399540501458,
"children": {
"TorchPolicy.sample_actions": {
"total": 70.33144727301783,
"count": 62553,
"self": 70.33144727301783
}
}
}
}
},
"workers": {
"total": 0.7847808760428734,
"count": 63763,
"self": 0.0,
"children": {
"worker_root": {
"total": 2236.2192501689883,
"count": 63763,
"is_parallel": true,
"self": 977.3635981469783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006373308999968685,
"count": 1,
"is_parallel": true,
"self": 0.003565505999972629,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028078029999960563,
"count": 8,
"is_parallel": true,
"self": 0.0028078029999960563
}
}
},
"UnityEnvironment.step": {
"total": 0.0795875250000222,
"count": 1,
"is_parallel": true,
"self": 0.0005199760000209608,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005479810000110774,
"count": 1,
"is_parallel": true,
"self": 0.0005479810000110774
},
"communicator.exchange": {
"total": 0.07685879799998929,
"count": 1,
"is_parallel": true,
"self": 0.07685879799998929
},
"steps_from_proto": {
"total": 0.0016607700000008663,
"count": 1,
"is_parallel": true,
"self": 0.00046866000002410146,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011921099999767648,
"count": 8,
"is_parallel": true,
"self": 0.0011921099999767648
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1258.85565202201,
"count": 63762,
"is_parallel": true,
"self": 31.391892611984304,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.8659867790235,
"count": 63762,
"is_parallel": true,
"self": 22.8659867790235
},
"communicator.exchange": {
"total": 1111.7141234210421,
"count": 63762,
"is_parallel": true,
"self": 1111.7141234210421
},
"steps_from_proto": {
"total": 92.8836492099602,
"count": 63762,
"is_parallel": true,
"self": 21.509790691946364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.37385851801383,
"count": 510096,
"is_parallel": true,
"self": 71.37385851801383
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 744.042473665966,
"count": 63763,
"self": 2.5651719339781494,
"children": {
"process_trajectory": {
"total": 161.86282079298502,
"count": 63763,
"self": 161.5522746969852,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3105460959998254,
"count": 2,
"self": 0.3105460959998254
}
}
},
"_update_policy": {
"total": 579.6144809390028,
"count": 453,
"self": 223.53539609595038,
"children": {
"TorchPPOOptimizer.update": {
"total": 356.0790848430524,
"count": 22800,
"self": 356.0790848430524
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.129998943535611e-07,
"count": 1,
"self": 9.129998943535611e-07
},
"TrainerController._save_models": {
"total": 0.08576774999983172,
"count": 1,
"self": 0.0013381119997575297,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08442963800007419,
"count": 1,
"self": 0.08442963800007419
}
}
}
}
}
}
}