chandc's picture
first attempt
09a7d59
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4156014323234558,
"min": 0.4156014323234558,
"max": 1.4807822704315186,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12434.794921875,
"min": 12434.794921875,
"max": 44921.01171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989905.0,
"min": 29952.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989905.0,
"min": 29952.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.536309540271759,
"min": -0.10927662253379822,
"max": 0.5385124087333679,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 146.94882202148438,
"min": -26.33566665649414,
"max": 150.24496459960938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.28527531027793884,
"min": -0.03896413743495941,
"max": 0.4150210916996002,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 78.16543579101562,
"min": -10.559281349182129,
"max": 98.36000061035156,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06999790042302469,
"min": 0.06477071107707667,
"max": 0.07240479739235597,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0499685063453703,
"min": 0.4716509862601538,
"max": 1.0544387443709031,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.026269603320138734,
"min": 0.0002696231156116831,
"max": 0.026269603320138734,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.394044049802081,
"min": 0.0029658542717285147,
"max": 0.394044049802081,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.531677489473333e-06,
"min": 7.531677489473333e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001129751623421,
"min": 0.0001129751623421,
"max": 0.0032254015248661997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251052666666666,
"min": 0.10251052666666666,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376579,
"min": 1.3886848,
"max": 2.4008914000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026080161400000005,
"min": 0.00026080161400000005,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003912024210000001,
"min": 0.003912024210000001,
"max": 0.10752586662,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008426743559539318,
"min": 0.008123093284666538,
"max": 0.4475361704826355,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1264011561870575,
"min": 0.11372330039739609,
"max": 3.1327531337738037,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 374.48148148148147,
"min": 355.8488372093023,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30333.0,
"min": 15984.0,
"max": 32689.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5489799819886685,
"min": -1.0000000521540642,
"max": 1.5976232365640097,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 123.91839855909348,
"min": -31.999601677060127,
"max": 137.39559834450483,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5489799819886685,
"min": -1.0000000521540642,
"max": 1.5976232365640097,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 123.91839855909348,
"min": -31.999601677060127,
"max": 137.39559834450483,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03329073642817093,
"min": 0.030792630440592352,
"max": 9.642984894104302,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6632589142536744,
"min": 2.432617804806796,
"max": 154.28775830566883,
"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": "1678194188",
"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=PyramidsTraining --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": "1678196381"
},
"total": 2193.6794462509997,
"count": 1,
"self": 0.47503050599971175,
"children": {
"run_training.setup": {
"total": 0.10669019699980709,
"count": 1,
"self": 0.10669019699980709
},
"TrainerController.start_learning": {
"total": 2193.097725548,
"count": 1,
"self": 1.3043341059656086,
"children": {
"TrainerController._reset_env": {
"total": 6.93937927800016,
"count": 1,
"self": 6.93937927800016
},
"TrainerController.advance": {
"total": 2184.766764263033,
"count": 63686,
"self": 1.3733662960221409,
"children": {
"env_step": {
"total": 1457.4448872961075,
"count": 63686,
"self": 1346.7758128621822,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.88478238095786,
"count": 63686,
"self": 4.600766612864845,
"children": {
"TorchPolicy.evaluate": {
"total": 105.28401576809301,
"count": 62551,
"self": 36.18954626808727,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.09446950000574,
"count": 62551,
"self": 69.09446950000574
}
}
}
}
},
"workers": {
"total": 0.7842920529674302,
"count": 63686,
"self": 0.0,
"children": {
"worker_root": {
"total": 2188.4415348099396,
"count": 63686,
"is_parallel": true,
"self": 955.2105349927806,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019495619999361224,
"count": 1,
"is_parallel": true,
"self": 0.0006645780003964319,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012849839995396906,
"count": 8,
"is_parallel": true,
"self": 0.0012849839995396906
}
}
},
"UnityEnvironment.step": {
"total": 0.0965733990001354,
"count": 1,
"is_parallel": true,
"self": 0.0005398600001171872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046447999966403586,
"count": 1,
"is_parallel": true,
"self": 0.00046447999966403586
},
"communicator.exchange": {
"total": 0.09386625200022536,
"count": 1,
"is_parallel": true,
"self": 0.09386625200022536
},
"steps_from_proto": {
"total": 0.0017028070001288143,
"count": 1,
"is_parallel": true,
"self": 0.00042977000020982814,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012730369999189861,
"count": 8,
"is_parallel": true,
"self": 0.0012730369999189861
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1233.230999817159,
"count": 63685,
"is_parallel": true,
"self": 31.32020853828635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.001654097919072,
"count": 63685,
"is_parallel": true,
"self": 23.001654097919072
},
"communicator.exchange": {
"total": 1088.3429519950846,
"count": 63685,
"is_parallel": true,
"self": 1088.3429519950846
},
"steps_from_proto": {
"total": 90.56618518586902,
"count": 63685,
"is_parallel": true,
"self": 21.438625820667312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 69.1275593652017,
"count": 509480,
"is_parallel": true,
"self": 69.1275593652017
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 725.9485106709035,
"count": 63686,
"self": 2.3994166478887564,
"children": {
"process_trajectory": {
"total": 161.54399439901636,
"count": 63686,
"self": 161.31594180001548,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2280525990008755,
"count": 2,
"self": 0.2280525990008755
}
}
},
"_update_policy": {
"total": 562.0050996239984,
"count": 444,
"self": 213.9558835409839,
"children": {
"TorchPPOOptimizer.update": {
"total": 348.04921608301447,
"count": 22794,
"self": 348.04921608301447
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0420008038636297e-06,
"count": 1,
"self": 1.0420008038636297e-06
},
"TrainerController._save_models": {
"total": 0.08724685900051554,
"count": 1,
"self": 0.0014608780002163257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08578598100029922,
"count": 1,
"self": 0.08578598100029922
}
}
}
}
}
}
}