martomor's picture
First Push
b1274ed verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.9414815902709961,
"min": 0.9414815902709961,
"max": 1.446037769317627,
"count": 3
},
"Pyramids.Policy.Entropy.sum": {
"value": 28199.255859375,
"min": 28199.255859375,
"max": 43867.0,
"count": 3
},
"Pyramids.Step.mean": {
"value": 89884.0,
"min": 29952.0,
"max": 89884.0,
"count": 3
},
"Pyramids.Step.sum": {
"value": 89884.0,
"min": 29952.0,
"max": 89884.0,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.08104833960533142,
"min": -0.08104833960533142,
"max": 0.008638164028525352,
"count": 3
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -19.532649993896484,
"min": -19.532649993896484,
"max": 2.0472447872161865,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.18087421357631683,
"min": 0.18087421357631683,
"max": 0.33767834305763245,
"count": 3
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 43.5906867980957,
"min": 43.5906867980957,
"max": 80.02976989746094,
"count": 3
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06858786123453854,
"min": 0.06858786123453854,
"max": 0.07131118585179906,
"count": 3
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.754466473579924,
"min": 0.4856381571537885,
"max": 0.754466473579924,
"count": 3
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.001702722761648657,
"min": 0.0007380032792004694,
"max": 0.006664231015507204,
"count": 3
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.018729950378135227,
"min": 0.005166022954403286,
"max": 0.04664961710855042,
"count": 3
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.42967115980909e-05,
"min": 7.42967115980909e-05,
"max": 0.0002515063018788571,
"count": 3
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0008172638275789998,
"min": 0.0008172638275789998,
"max": 0.0017605441131519997,
"count": 3
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.12476554545454546,
"min": 0.12476554545454546,
"max": 0.1838354285714286,
"count": 3
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3724210000000001,
"min": 1.0911359999999999,
"max": 1.3724210000000001,
"count": 3
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0024840779909090912,
"min": 0.0024840779909090912,
"max": 0.008385159314285713,
"count": 3
},
"Pyramids.Policy.Beta.sum": {
"value": 0.027324857900000003,
"min": 0.027324857900000003,
"max": 0.058696115199999996,
"count": 3
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.10290222615003586,
"min": 0.10290222615003586,
"max": 0.4093218147754669,
"count": 3
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 1.1319245100021362,
"min": 1.1319245100021362,
"max": 2.865252733230591,
"count": 3
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 959.8235294117648,
"min": 959.8235294117648,
"max": 999.0,
"count": 3
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32634.0,
"min": 15984.0,
"max": 32634.0,
"count": 3
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.7842412284191917,
"min": -1.0000000521540642,
"max": -0.7842412284191917,
"count": 3
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -26.664201766252518,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.7842412284191917,
"min": -1.0000000521540642,
"max": -0.7842412284191917,
"count": 3
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -26.664201766252518,
"min": -32.000001668930054,
"max": -16.000000834465027,
"count": 3
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.1678054282332169,
"min": 1.1678054282332169,
"max": 8.41881376132369,
"count": 3
},
"Pyramids.Policy.RndReward.sum": {
"value": 39.70538455992937,
"min": 39.70538455992937,
"max": 134.70102018117905,
"count": 3
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1729894719",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729894927"
},
"total": 208.36145361000007,
"count": 1,
"self": 0.49138315700002977,
"children": {
"run_training.setup": {
"total": 0.07943155500004195,
"count": 1,
"self": 0.07943155500004195
},
"TrainerController.start_learning": {
"total": 207.790638898,
"count": 1,
"self": 0.13150964000328713,
"children": {
"TrainerController._reset_env": {
"total": 5.557687069999986,
"count": 1,
"self": 5.557687069999986
},
"TrainerController.advance": {
"total": 201.92397122099675,
"count": 6278,
"self": 0.14175341400232355,
"children": {
"env_step": {
"total": 131.99449397899616,
"count": 6278,
"self": 116.04901857898801,
"children": {
"SubprocessEnvManager._take_step": {
"total": 15.86663412000729,
"count": 6278,
"self": 0.4627615400084437,
"children": {
"TorchPolicy.evaluate": {
"total": 15.403872579998847,
"count": 6273,
"self": 15.403872579998847
}
}
},
"workers": {
"total": 0.07884128000085866,
"count": 6278,
"self": 0.0,
"children": {
"worker_root": {
"total": 207.23475833199905,
"count": 6278,
"is_parallel": true,
"self": 102.78258810099936,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025758429999882537,
"count": 1,
"is_parallel": true,
"self": 0.0007145279999463128,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001861315000041941,
"count": 8,
"is_parallel": true,
"self": 0.001861315000041941
}
}
},
"UnityEnvironment.step": {
"total": 0.0488695579999785,
"count": 1,
"is_parallel": true,
"self": 0.0006371669999793994,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004484579999939342,
"count": 1,
"is_parallel": true,
"self": 0.0004484579999939342
},
"communicator.exchange": {
"total": 0.04597271400001546,
"count": 1,
"is_parallel": true,
"self": 0.04597271400001546
},
"steps_from_proto": {
"total": 0.0018112189999897055,
"count": 1,
"is_parallel": true,
"self": 0.000379226000120525,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014319929998691805,
"count": 8,
"is_parallel": true,
"self": 0.0014319929998691805
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 104.45217023099968,
"count": 6277,
"is_parallel": true,
"self": 3.2656338329992423,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.3425917509984515,
"count": 6277,
"is_parallel": true,
"self": 2.3425917509984515
},
"communicator.exchange": {
"total": 89.27179947400197,
"count": 6277,
"is_parallel": true,
"self": 89.27179947400197
},
"steps_from_proto": {
"total": 9.572145173000024,
"count": 6277,
"is_parallel": true,
"self": 1.944718867993629,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.627426305006395,
"count": 50216,
"is_parallel": true,
"self": 7.627426305006395
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 69.78772382799826,
"count": 6278,
"self": 0.16071945500078755,
"children": {
"process_trajectory": {
"total": 12.447930613997642,
"count": 6278,
"self": 12.447930613997642
},
"_update_policy": {
"total": 57.179073758999834,
"count": 29,
"self": 31.990639839000153,
"children": {
"TorchPPOOptimizer.update": {
"total": 25.18843391999968,
"count": 2331,
"self": 25.18843391999968
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.859999181571766e-07,
"count": 1,
"self": 9.859999181571766e-07
},
"TrainerController._save_models": {
"total": 0.1774699810000584,
"count": 1,
"self": 0.001371413000015309,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1760985680000431,
"count": 1,
"self": 0.1760985680000431
}
}
}
}
}
}
}