ppo-Pyramids / run_logs /timers.json
veselovich's picture
First Push
a7459a2 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4028690755367279,
"min": 0.3839576840400696,
"max": 1.4718403816223145,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12053.8427734375,
"min": 11469.583984375,
"max": 44649.75,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.46272510290145874,
"min": -0.10088693350553513,
"max": 0.5144004821777344,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 123.54759979248047,
"min": -24.313751220703125,
"max": 142.4889373779297,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.054513610899448395,
"min": 0.004410456866025925,
"max": 0.3029234707355499,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.555133819580078,
"min": 1.1952338218688965,
"max": 71.79286193847656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06731519577766046,
"min": 0.06493265259519426,
"max": 0.07229962383440001,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0097279366649068,
"min": 0.47201306267956605,
"max": 1.0543982308145667,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015889120835345237,
"min": 0.0007542598108204006,
"max": 0.017881303882470136,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23833681253017858,
"min": 0.00850774729675824,
"max": 0.2503382543545819,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.493257502279999e-06,
"min": 7.493257502279999e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011239886253419998,
"min": 0.00011239886253419998,
"max": 0.0036337417887528,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249772,
"min": 0.10249772,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374658,
"min": 1.3691136000000002,
"max": 2.6112471999999998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000259522228,
"min": 0.000259522228,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038928334199999997,
"min": 0.0038928334199999997,
"max": 0.12114359527999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0080641470849514,
"min": 0.0080641470849514,
"max": 0.3687760829925537,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12096220254898071,
"min": 0.1178002655506134,
"max": 2.581432580947876,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 411.4054054054054,
"min": 364.0779220779221,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30444.0,
"min": 15984.0,
"max": 33246.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4228218918385571,
"min": -1.0000000521540642,
"max": 1.584797354415059,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 103.86599810421467,
"min": -32.000001668930054,
"max": 134.49219822138548,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4228218918385571,
"min": -1.0000000521540642,
"max": 1.584797354415059,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 103.86599810421467,
"min": -32.000001668930054,
"max": 134.49219822138548,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.034097158755909344,
"min": 0.03239556195215922,
"max": 7.835193618200719,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.489092589181382,
"min": 2.462062708364101,
"max": 125.36309789121151,
"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": "1750127043",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750129127"
},
"total": 2083.228702469,
"count": 1,
"self": 0.4913267529996119,
"children": {
"run_training.setup": {
"total": 0.02533466599993517,
"count": 1,
"self": 0.02533466599993517
},
"TrainerController.start_learning": {
"total": 2082.71204105,
"count": 1,
"self": 1.179821173997425,
"children": {
"TrainerController._reset_env": {
"total": 2.660394408000002,
"count": 1,
"self": 2.660394408000002
},
"TrainerController.advance": {
"total": 2078.7916236960027,
"count": 63677,
"self": 1.2766036009770687,
"children": {
"env_step": {
"total": 1433.853216368021,
"count": 63677,
"self": 1292.1541633689105,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.95069836910898,
"count": 63677,
"self": 4.43945910610978,
"children": {
"TorchPolicy.evaluate": {
"total": 136.5112392629992,
"count": 62539,
"self": 136.5112392629992
}
}
},
"workers": {
"total": 0.748354630001586,
"count": 63677,
"self": 0.0,
"children": {
"worker_root": {
"total": 2078.1257153199986,
"count": 63677,
"is_parallel": true,
"self": 891.7458141299996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0026160790000631096,
"count": 1,
"is_parallel": true,
"self": 0.0007619500001965207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018541289998665889,
"count": 8,
"is_parallel": true,
"self": 0.0018541289998665889
}
}
},
"UnityEnvironment.step": {
"total": 0.04938379600002918,
"count": 1,
"is_parallel": true,
"self": 0.000568581999914386,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004923240001062368,
"count": 1,
"is_parallel": true,
"self": 0.0004923240001062368
},
"communicator.exchange": {
"total": 0.046664227000064784,
"count": 1,
"is_parallel": true,
"self": 0.046664227000064784
},
"steps_from_proto": {
"total": 0.0016586629999437719,
"count": 1,
"is_parallel": true,
"self": 0.00034517500012043456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013134879998233373,
"count": 8,
"is_parallel": true,
"self": 0.0013134879998233373
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1186.379901189999,
"count": 63676,
"is_parallel": true,
"self": 30.746652911999945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.110281826000573,
"count": 63676,
"is_parallel": true,
"self": 22.110281826000573
},
"communicator.exchange": {
"total": 1040.8987813610431,
"count": 63676,
"is_parallel": true,
"self": 1040.8987813610431
},
"steps_from_proto": {
"total": 92.62418509095528,
"count": 63676,
"is_parallel": true,
"self": 18.294083820853302,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.33010127010198,
"count": 509408,
"is_parallel": true,
"self": 74.33010127010198
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 643.6618037270043,
"count": 63677,
"self": 2.282308182030647,
"children": {
"process_trajectory": {
"total": 121.84186578797721,
"count": 63677,
"self": 121.60345090997703,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23841487800018513,
"count": 2,
"self": 0.23841487800018513
}
}
},
"_update_policy": {
"total": 519.5376297569965,
"count": 448,
"self": 288.314170439985,
"children": {
"TorchPPOOptimizer.update": {
"total": 231.22345931701147,
"count": 22749,
"self": 231.22345931701147
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.130000423989259e-07,
"count": 1,
"self": 8.130000423989259e-07
},
"TrainerController._save_models": {
"total": 0.08020095900019442,
"count": 1,
"self": 0.0013007030001972453,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07890025599999717,
"count": 1,
"self": 0.07890025599999717
}
}
}
}
}
}
}