ppo-Pyramids / run_logs /timers.json
AMZ2004's picture
Pyramids trained with optimized hyperparameters
7d60245 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.5640696287155151,
"min": 1.5640696287155151,
"max": 1.6093742847442627,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 12988.0341796875,
"min": 12988.0341796875,
"max": 19321.767578125,
"count": 10
},
"Pyramids.Step.mean": {
"value": 99968.0,
"min": 9984.0,
"max": 99968.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 99968.0,
"min": 9984.0,
"max": 99968.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.014162606559693813,
"min": -0.014162606559693813,
"max": 0.05569199100136757,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.147171139717102,
"min": -1.147171139717102,
"max": 4.511051177978516,
"count": 10
},
"Pyramids.Policy.CuriosityValueEstimate.mean": {
"value": 0.4329676330089569,
"min": -0.1498025506734848,
"max": 0.4329676330089569,
"count": 10
},
"Pyramids.Policy.CuriosityValueEstimate.sum": {
"value": 35.070377349853516,
"min": -12.13400650024414,
"max": 35.070377349853516,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 6
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 15984.0,
"min": 15984.0,
"max": 15984.0,
"count": 6
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 7
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -1.0000000521540642,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -1.0000000521540642,
"count": 7
},
"Pyramids.Policy.CuriosityReward.mean": {
"value": 7.927281200885773,
"min": 0.0,
"max": 17.421521808952093,
"count": 7
},
"Pyramids.Policy.CuriosityReward.sum": {
"value": 126.83649921417236,
"min": 0.0,
"max": 278.7443489432335,
"count": 7
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.03462031208765657,
"min": 0.03462031208765657,
"max": 0.03916700262879391,
"count": 4
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.03462031208765657,
"min": 0.03462031208765657,
"max": 0.03916700262879391,
"count": 4
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0025030783659150432,
"min": 0.0025030783659150432,
"max": 0.009131395406010307,
"count": 4
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0025030783659150432,
"min": 0.0025030783659150432,
"max": 0.009131395406010307,
"count": 4
},
"Pyramids.Policy.LearningRate.mean": {
"value": 3.5424088191999986e-05,
"min": 3.5424088191999986e-05,
"max": 0.00023356802214399998,
"count": 4
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.5424088191999986e-05,
"min": 3.5424088191999986e-05,
"max": 0.00023356802214399998,
"count": 4
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.111808,
"min": 0.111808,
"max": 0.17785600000000001,
"count": 4
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.111808,
"min": 0.111808,
"max": 0.17785600000000001,
"count": 4
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005992191999999999,
"min": 0.0005992191999999999,
"max": 0.003895014400000001,
"count": 4
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0005992191999999999,
"min": 0.0005992191999999999,
"max": 0.003895014400000001,
"count": 4
},
"Pyramids.Losses.CuriosityForwardLoss.mean": {
"value": 0.3518896017425744,
"min": 0.3518896017425744,
"max": 2.242860344953315,
"count": 4
},
"Pyramids.Losses.CuriosityForwardLoss.sum": {
"value": 0.3518896017425744,
"min": 0.3518896017425744,
"max": 2.242860344953315,
"count": 4
},
"Pyramids.Losses.CuriosityInverseLoss.mean": {
"value": 0.6723511958307073,
"min": 0.6723511958307073,
"max": 1.281446327534757,
"count": 4
},
"Pyramids.Losses.CuriosityInverseLoss.sum": {
"value": 0.6723511958307073,
"min": 0.6723511958307073,
"max": 1.281446327534757,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1754241121",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/miniconda/envs/myenv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --force",
"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": "1754241423"
},
"total": 301.85832204100006,
"count": 1,
"self": 0.628613802000018,
"children": {
"run_training.setup": {
"total": 0.024354811999955928,
"count": 1,
"self": 0.024354811999955928
},
"TrainerController.start_learning": {
"total": 301.2053534270001,
"count": 1,
"self": 0.3426342729899261,
"children": {
"TrainerController._reset_env": {
"total": 2.4836427920001825,
"count": 1,
"self": 2.4836427920001825
},
"TrainerController.advance": {
"total": 298.14895278000995,
"count": 6300,
"self": 0.15078533701853303,
"children": {
"env_step": {
"total": 297.9981674429914,
"count": 6300,
"self": 250.2689982449865,
"children": {
"SubprocessEnvManager._take_step": {
"total": 47.579949131998546,
"count": 6300,
"self": 1.4253032550025182,
"children": {
"TorchPolicy.evaluate": {
"total": 46.15464587699603,
"count": 6300,
"self": 46.15464587699603
}
}
},
"workers": {
"total": 0.1492200660063645,
"count": 6300,
"self": 0.0,
"children": {
"worker_root": {
"total": 300.2425207940021,
"count": 6300,
"is_parallel": true,
"self": 168.13723427800005,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020754580000357237,
"count": 1,
"is_parallel": true,
"self": 0.0006986869998399925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013767710001957312,
"count": 8,
"is_parallel": true,
"self": 0.0013767710001957312
}
}
},
"UnityEnvironment.step": {
"total": 0.07565734500008148,
"count": 1,
"is_parallel": true,
"self": 0.0007306909999442723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005960099999811064,
"count": 1,
"is_parallel": true,
"self": 0.0005960099999811064
},
"communicator.exchange": {
"total": 0.0720293340000353,
"count": 1,
"is_parallel": true,
"self": 0.0720293340000353
},
"steps_from_proto": {
"total": 0.002301310000120793,
"count": 1,
"is_parallel": true,
"self": 0.0007114519999049662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001589858000215827,
"count": 8,
"is_parallel": true,
"self": 0.001589858000215827
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 132.10528651600202,
"count": 6299,
"is_parallel": true,
"self": 4.47634222900524,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.044544308001605,
"count": 6299,
"is_parallel": true,
"self": 3.044544308001605
},
"communicator.exchange": {
"total": 111.71012362799934,
"count": 6299,
"is_parallel": true,
"self": 111.71012362799934
},
"steps_from_proto": {
"total": 12.874276350995842,
"count": 6299,
"is_parallel": true,
"self": 2.818148850961279,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.056127500034563,
"count": 50392,
"is_parallel": true,
"self": 10.056127500034563
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021401000003606896,
"count": 1,
"self": 0.00021401000003606896,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 295.3540494310448,
"count": 351019,
"is_parallel": true,
"self": 7.361699394021116,
"children": {
"process_trajectory": {
"total": 164.23620037202363,
"count": 351019,
"is_parallel": true,
"self": 163.1784165290237,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0577838429999247,
"count": 2,
"is_parallel": true,
"self": 1.0577838429999247
}
}
},
"_update_policy": {
"total": 123.75614966500007,
"count": 4,
"is_parallel": true,
"self": 65.40281548999883,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.35333417500124,
"count": 513,
"is_parallel": true,
"self": 58.35333417500124
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22990957199999684,
"count": 1,
"self": 0.010770060999902853,
"children": {
"RLTrainer._checkpoint": {
"total": 0.219139511000094,
"count": 1,
"self": 0.219139511000094
}
}
}
}
}
}
}