AliCampbellKhaya's picture
First Training
d5908a5
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4630157947540283,
"min": 0.4630157947540283,
"max": 1.4419184923171997,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13986.78125,
"min": 13791.017578125,
"max": 43742.0390625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989936.0,
"min": 29952.0,
"max": 989936.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989936.0,
"min": 29952.0,
"max": 989936.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5749961137771606,
"min": -0.2187630981206894,
"max": 0.6283597946166992,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 160.42391967773438,
"min": -51.84685516357422,
"max": 174.0556640625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0021024742163717747,
"min": -0.027536729350686073,
"max": 0.2831006944179535,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.5865902900695801,
"min": -7.737821102142334,
"max": 67.09486389160156,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0673140517363684,
"min": 0.0649843429793579,
"max": 0.0733946210034781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.009710776045526,
"min": 0.47664150851377257,
"max": 1.1000767868439045,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015053894966757048,
"min": 0.0002415041919079904,
"max": 0.018734257376525506,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22580842450135571,
"min": 0.0028980503028958847,
"max": 0.2622796032713571,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.540617486493334e-06,
"min": 7.540617486493334e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011310926229740002,
"min": 0.00011310926229740002,
"max": 0.0035080481306506996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251350666666668,
"min": 0.10251350666666668,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5377026000000003,
"min": 1.3886848,
"max": 2.5693493000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002610993160000001,
"min": 0.0002610993160000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003916489740000001,
"min": 0.003916489740000001,
"max": 0.11695799507000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008719777688384056,
"min": 0.008682888932526112,
"max": 0.4699053466320038,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1307966709136963,
"min": 0.12156044691801071,
"max": 3.289337396621704,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 324.6263736263736,
"min": 317.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29541.0,
"min": 15984.0,
"max": 32589.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5874329490157275,
"min": -1.0000000521540642,
"max": 1.6783110954695277,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 144.4563983604312,
"min": -29.892401665449142,
"max": 155.51819874346256,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5874329490157275,
"min": -1.0000000521540642,
"max": 1.6783110954695277,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 144.4563983604312,
"min": -29.892401665449142,
"max": 155.51819874346256,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02916793167129911,
"min": 0.028443337949890218,
"max": 10.004269925877452,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.654281782088219,
"min": 2.654281782088219,
"max": 160.06831881403923,
"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": "1683732281",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1683734502"
},
"total": 2221.538925906,
"count": 1,
"self": 1.146305193999524,
"children": {
"run_training.setup": {
"total": 0.03776359699986642,
"count": 1,
"self": 0.03776359699986642
},
"TrainerController.start_learning": {
"total": 2220.3548571150004,
"count": 1,
"self": 1.2302630120138929,
"children": {
"TrainerController._reset_env": {
"total": 4.3441247400000975,
"count": 1,
"self": 4.3441247400000975
},
"TrainerController.advance": {
"total": 2214.645331082986,
"count": 63934,
"self": 1.2724304910097999,
"children": {
"env_step": {
"total": 1592.2250474039915,
"count": 63934,
"self": 1487.5683920021092,
"children": {
"SubprocessEnvManager._take_step": {
"total": 103.88278873892796,
"count": 63934,
"self": 4.6611831277764395,
"children": {
"TorchPolicy.evaluate": {
"total": 99.22160561115152,
"count": 62560,
"self": 99.22160561115152
}
}
},
"workers": {
"total": 0.7738666629543332,
"count": 63934,
"self": 0.0,
"children": {
"worker_root": {
"total": 2215.271935214035,
"count": 63934,
"is_parallel": true,
"self": 836.9961070870754,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017853259996627457,
"count": 1,
"is_parallel": true,
"self": 0.0005540049992305285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012313210004322173,
"count": 8,
"is_parallel": true,
"self": 0.0012313210004322173
}
}
},
"UnityEnvironment.step": {
"total": 0.07603387199969802,
"count": 1,
"is_parallel": true,
"self": 0.0005278839998936746,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004643859997486288,
"count": 1,
"is_parallel": true,
"self": 0.0004643859997486288
},
"communicator.exchange": {
"total": 0.07328845299980458,
"count": 1,
"is_parallel": true,
"self": 0.07328845299980458
},
"steps_from_proto": {
"total": 0.0017531490002511418,
"count": 1,
"is_parallel": true,
"self": 0.0003385030004210421,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014146459998300998,
"count": 8,
"is_parallel": true,
"self": 0.0014146459998300998
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.2758281269594,
"count": 63933,
"is_parallel": true,
"self": 30.948991695123368,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.97672127792339,
"count": 63933,
"is_parallel": true,
"self": 21.97672127792339
},
"communicator.exchange": {
"total": 1230.419165196839,
"count": 63933,
"is_parallel": true,
"self": 1230.419165196839
},
"steps_from_proto": {
"total": 94.93094995707361,
"count": 63933,
"is_parallel": true,
"self": 19.272951226313126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.65799873076048,
"count": 511464,
"is_parallel": true,
"self": 75.65799873076048
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 621.1478531879848,
"count": 63934,
"self": 2.381411969041892,
"children": {
"process_trajectory": {
"total": 105.61841562294057,
"count": 63934,
"self": 105.36049167594001,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2579239470005632,
"count": 2,
"self": 0.2579239470005632
}
}
},
"_update_policy": {
"total": 513.1480255960023,
"count": 447,
"self": 328.57302488897403,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.57500070702827,
"count": 22791,
"self": 184.57500070702827
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.139000232797116e-06,
"count": 1,
"self": 1.139000232797116e-06
},
"TrainerController._save_models": {
"total": 0.13513714100008656,
"count": 1,
"self": 0.0019622149993665516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13317492600072,
"count": 1,
"self": 0.13317492600072
}
}
}
}
}
}
}