ppo-Pyramids / run_logs /timers.json
victorivus's picture
First Push
18381a5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.16881319880485535,
"min": 0.16881319880485535,
"max": 1.4843875169754028,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 5072.4990234375,
"min": 5072.4990234375,
"max": 45030.37890625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989915.0,
"min": 29937.0,
"max": 989915.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989915.0,
"min": 29937.0,
"max": 989915.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6621834635734558,
"min": -0.06501097977161407,
"max": 0.7958129644393921,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 187.39791870117188,
"min": -15.60263442993164,
"max": 230.78575134277344,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.07879692316055298,
"min": 0.05010196566581726,
"max": 0.3619806468486786,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 22.299530029296875,
"min": 14.279060363769531,
"max": 85.78941345214844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07065680086765477,
"min": 0.06551585932417461,
"max": 0.0739751593415242,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9891952121471668,
"min": 0.5123647982395125,
"max": 1.053095702372957,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01592079289414051,
"min": 0.0010158400226120733,
"max": 0.018124275340877034,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22289110051796715,
"min": 0.011174240248732805,
"max": 0.25421649585283984,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.2640561757621424e-05,
"min": 1.2640561757621424e-05,
"max": 0.0004920559301602429,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00017696786460669994,
"min": 0.00017696786460669994,
"max": 0.006267067646586499,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252809285714286,
"min": 0.10252809285714286,
"max": 0.1984111857142857,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4353933,
"min": 1.3888783,
"max": 2.7074571,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002625564764285714,
"min": 0.0002625564764285714,
"max": 0.009841277452857141,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00367579067,
"min": 0.00367579067,
"max": 0.12535600865000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.07119981199502945,
"min": 0.05971728637814522,
"max": 0.4365963935852051,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.9967973232269287,
"min": 0.8360419869422913,
"max": 3.0561747550964355,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 275.7567567567568,
"min": 236.01612903225808,
"max": 987.8181818181819,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30609.0,
"min": 16736.0,
"max": 33174.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6501254377039996,
"min": -0.9281273247166113,
"max": 1.7512881235551025,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 181.51379814743996,
"min": -30.628201715648174,
"max": 216.3923983424902,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6501254377039996,
"min": -0.9281273247166113,
"max": 1.7512881235551025,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 181.51379814743996,
"min": -30.628201715648174,
"max": 216.3923983424902,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.19460642154392024,
"min": 0.15389467096840964,
"max": 7.94310062334818,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 21.406706369831227,
"min": 18.2279657284962,
"max": 135.03271059691906,
"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": "1678288998",
"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": "1.22.4",
"end_time_seconds": "1678291945"
},
"total": 2946.9204699170004,
"count": 1,
"self": 0.5262085620001926,
"children": {
"run_training.setup": {
"total": 0.1306887949999691,
"count": 1,
"self": 0.1306887949999691
},
"TrainerController.start_learning": {
"total": 2946.2635725600003,
"count": 1,
"self": 2.0137008059582513,
"children": {
"TrainerController._reset_env": {
"total": 7.779291500999989,
"count": 1,
"self": 7.779291500999989
},
"TrainerController.advance": {
"total": 2936.3515792580406,
"count": 64798,
"self": 1.962288459013962,
"children": {
"env_step": {
"total": 2009.6071112040377,
"count": 64798,
"self": 1844.0147678580167,
"children": {
"SubprocessEnvManager._take_step": {
"total": 164.40041095600463,
"count": 64798,
"self": 5.929853042920058,
"children": {
"TorchPolicy.evaluate": {
"total": 158.47055791308458,
"count": 62563,
"self": 46.48018259515766,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.99037531792692,
"count": 62563,
"self": 111.99037531792692
}
}
}
}
},
"workers": {
"total": 1.1919323900162908,
"count": 64798,
"self": 0.0,
"children": {
"worker_root": {
"total": 2938.94512436497,
"count": 64798,
"is_parallel": true,
"self": 1241.5021901050661,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019074990000262915,
"count": 1,
"is_parallel": true,
"self": 0.0007020169996394543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012054820003868372,
"count": 8,
"is_parallel": true,
"self": 0.0012054820003868372
}
}
},
"UnityEnvironment.step": {
"total": 0.04861067699994237,
"count": 1,
"is_parallel": true,
"self": 0.0005960029998277605,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007017640000412939,
"count": 1,
"is_parallel": true,
"self": 0.0007017640000412939
},
"communicator.exchange": {
"total": 0.04555135600003268,
"count": 1,
"is_parallel": true,
"self": 0.04555135600003268
},
"steps_from_proto": {
"total": 0.0017615540000406327,
"count": 1,
"is_parallel": true,
"self": 0.00045664500044040324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013049089996002294,
"count": 8,
"is_parallel": true,
"self": 0.0013049089996002294
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1697.442934259904,
"count": 64797,
"is_parallel": true,
"self": 37.87593394190617,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.730551564978214,
"count": 64797,
"is_parallel": true,
"self": 26.730551564978214
},
"communicator.exchange": {
"total": 1522.134619247014,
"count": 64797,
"is_parallel": true,
"self": 1522.134619247014
},
"steps_from_proto": {
"total": 110.70182950600565,
"count": 64797,
"is_parallel": true,
"self": 28.053597778081667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 82.64823172792399,
"count": 518376,
"is_parallel": true,
"self": 82.64823172792399
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 924.782179594989,
"count": 64798,
"self": 3.7140458680230495,
"children": {
"process_trajectory": {
"total": 230.0486109259673,
"count": 64798,
"self": 229.80043146596654,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24817946000075608,
"count": 2,
"self": 0.24817946000075608
}
}
},
"_update_policy": {
"total": 691.0195228009986,
"count": 461,
"self": 257.38561369098943,
"children": {
"TorchPPOOptimizer.update": {
"total": 433.6339091100092,
"count": 22818,
"self": 433.6339091100092
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.007000719255302e-06,
"count": 1,
"self": 1.007000719255302e-06
},
"TrainerController._save_models": {
"total": 0.11899998800072353,
"count": 1,
"self": 0.0010169850011152448,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11798300299960829,
"count": 1,
"self": 0.11798300299960829
}
}
}
}
}
}
}