ppo-PyramidsRND / run_logs /timers.json
agercas's picture
Upload first trained model
90ec6c6
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5207598209381104,
"min": 0.5004580020904541,
"max": 1.3765321969985962,
"count": 35
},
"Pyramids.Policy.Entropy.sum": {
"value": 15597.798828125,
"min": 15005.7333984375,
"max": 41758.48046875,
"count": 35
},
"Pyramids.Step.mean": {
"value": 1049978.0,
"min": 29931.0,
"max": 1049978.0,
"count": 35
},
"Pyramids.Step.sum": {
"value": 1049978.0,
"min": 29931.0,
"max": 1049978.0,
"count": 35
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5057579874992371,
"min": -0.17100189626216888,
"max": 0.5057579874992371,
"count": 35
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 135.03738403320312,
"min": -40.52745056152344,
"max": 135.03738403320312,
"count": 35
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.006927202921360731,
"min": 0.006927202921360731,
"max": 0.3774693012237549,
"count": 35
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.8495632410049438,
"min": 1.8495632410049438,
"max": 90.97010040283203,
"count": 35
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06930331179826665,
"min": 0.06602892784138209,
"max": 0.07550924130229793,
"count": 35
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9702463651757331,
"min": 0.5285646891160855,
"max": 1.0811577959211005,
"count": 35
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012651403900867695,
"min": 0.00019788654721013296,
"max": 0.012972512797245546,
"count": 35
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17711965461214774,
"min": 0.0027704116609418615,
"max": 0.1945876919586832,
"count": 35
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00019642052738364524,
"min": 0.00019642052738364524,
"max": 0.0002984112719581476,
"count": 35
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.002749887383371033,
"min": 0.0020888789037070334,
"max": 0.004010936963021033,
"count": 35
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16547349761904764,
"min": 0.16547349761904764,
"max": 0.19947042380952382,
"count": 35
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.316628966666667,
"min": 1.3962929666666668,
"max": 2.736978966666667,
"count": 35
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006550802412142857,
"min": 0.006550802412142857,
"max": 0.009947095338571427,
"count": 35
},
"Pyramids.Policy.Beta.sum": {
"value": 0.09171123377,
"min": 0.06962966737,
"max": 0.13370419876999998,
"count": 35
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010899919085204601,
"min": 0.010899919085204601,
"max": 0.6370700001716614,
"count": 35
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15259887278079987,
"min": 0.15259887278079987,
"max": 4.459489822387695,
"count": 35
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 386.29487179487177,
"min": 386.29487179487177,
"max": 998.5333333333333,
"count": 35
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30131.0,
"min": 16602.0,
"max": 32849.0,
"count": 35
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5614701022768949,
"min": -0.9999000527895987,
"max": 1.5614701022768949,
"count": 35
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 120.23319787532091,
"min": -31.99680168926716,
"max": 120.23319787532091,
"count": 35
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5614701022768949,
"min": -0.9999000527895987,
"max": 1.5614701022768949,
"count": 35
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 120.23319787532091,
"min": -31.99680168926716,
"max": 120.23319787532091,
"count": 35
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04446493664566675,
"min": 0.04446493664566675,
"max": 12.100429093136507,
"count": 35
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.42380012171634,
"min": 3.42380012171634,
"max": 205.70729458332062,
"count": 35
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 35
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 35
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674299325",
"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": "1674302377"
},
"total": 3051.3855418249996,
"count": 1,
"self": 10.014411622999887,
"children": {
"run_training.setup": {
"total": 0.13206189800001766,
"count": 1,
"self": 0.13206189800001766
},
"TrainerController.start_learning": {
"total": 3041.239068304,
"count": 1,
"self": 2.1299211409955205,
"children": {
"TrainerController._reset_env": {
"total": 7.663396111000054,
"count": 1,
"self": 7.663396111000054
},
"TrainerController.advance": {
"total": 3031.0904949640044,
"count": 67168,
"self": 2.0442464060661223,
"children": {
"env_step": {
"total": 1883.9433534119523,
"count": 67168,
"self": 1754.7116765139497,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.81278751299413,
"count": 67168,
"self": 6.4501790019690475,
"children": {
"TorchPolicy.evaluate": {
"total": 121.36260851102509,
"count": 66190,
"self": 26.72961423405775,
"children": {
"TorchPolicy.sample_actions": {
"total": 94.63299427696734,
"count": 66190,
"self": 94.63299427696734
}
}
}
}
},
"workers": {
"total": 1.4188893850085833,
"count": 67167,
"self": 0.0,
"children": {
"worker_root": {
"total": 3035.5394308409345,
"count": 67167,
"is_parallel": true,
"self": 1430.2062941658942,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.01257594000003337,
"count": 1,
"is_parallel": true,
"self": 0.00448128100009626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00809465899993711,
"count": 8,
"is_parallel": true,
"self": 0.00809465899993711
}
}
},
"UnityEnvironment.step": {
"total": 0.05997939399998131,
"count": 1,
"is_parallel": true,
"self": 0.0005530550000116818,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004329500000039843,
"count": 1,
"is_parallel": true,
"self": 0.0004329500000039843
},
"communicator.exchange": {
"total": 0.05709933299999648,
"count": 1,
"is_parallel": true,
"self": 0.05709933299999648
},
"steps_from_proto": {
"total": 0.0018940559999691686,
"count": 1,
"is_parallel": true,
"self": 0.00044945799999140945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014445979999777592,
"count": 8,
"is_parallel": true,
"self": 0.0014445979999777592
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1605.3331366750404,
"count": 67166,
"is_parallel": true,
"self": 40.936131593147365,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.992778615993302,
"count": 67166,
"is_parallel": true,
"self": 22.992778615993302
},
"communicator.exchange": {
"total": 1405.5062630679722,
"count": 67166,
"is_parallel": true,
"self": 1405.5062630679722
},
"steps_from_proto": {
"total": 135.89796339792747,
"count": 67166,
"is_parallel": true,
"self": 31.198741272850725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 104.69922212507674,
"count": 537328,
"is_parallel": true,
"self": 104.69922212507674
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1145.1028951459862,
"count": 67167,
"self": 3.9967494749760135,
"children": {
"process_trajectory": {
"total": 198.46444601001173,
"count": 67167,
"self": 198.1275682120118,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3368777979999322,
"count": 2,
"self": 0.3368777979999322
}
}
},
"_update_policy": {
"total": 942.6416996609985,
"count": 478,
"self": 240.9754791899927,
"children": {
"TorchPPOOptimizer.update": {
"total": 701.6662204710058,
"count": 24111,
"self": 701.6662204710058
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9240001165599097e-06,
"count": 1,
"self": 1.9240001165599097e-06
},
"TrainerController._save_models": {
"total": 0.3552541639996889,
"count": 1,
"self": 0.003739501999461936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.35151466200022696,
"count": 1,
"self": 0.35151466200022696
}
}
}
}
}
}
}