{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4392893612384796,
"min": 0.4392893612384796,
"max": 1.3504714965820312,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13213.82421875,
"min": 13213.82421875,
"max": 40967.90234375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989931.0,
"min": 29904.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989931.0,
"min": 29904.0,
"max": 989931.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6779690384864807,
"min": -0.07883929461240768,
"max": 0.6779690384864807,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 195.2550811767578,
"min": -19.00027084350586,
"max": 196.60177612304688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0004023599030915648,
"min": 0.0004023599030915648,
"max": 0.40617644786834717,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.11587965488433838,
"min": 0.11587965488433838,
"max": 96.2638168334961,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0699233778619748,
"min": 0.06445257668803264,
"max": 0.07377521228391701,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9789272900676473,
"min": 0.4876470998392558,
"max": 1.0582884234415058,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01553540536742501,
"min": 0.0019775584867879527,
"max": 0.017130707905467023,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21749567514395013,
"min": 0.025052928665174737,
"max": 0.2398299106765383,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.620568888414291e-06,
"min": 7.620568888414291e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010668796443780007,
"min": 0.00010668796443780007,
"max": 0.0035072039309320996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254015714285716,
"min": 0.10254015714285716,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355622000000003,
"min": 1.3886848,
"max": 2.5690679,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026376169857142873,
"min": 0.00026376169857142873,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003692663780000002,
"min": 0.003692663780000002,
"max": 0.11692988321,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010193528607487679,
"min": 0.010193528607487679,
"max": 0.5258510708808899,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1427094042301178,
"min": 0.1427094042301178,
"max": 3.680957555770874,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 267.9811320754717,
"min": 267.9811320754717,
"max": 990.0588235294117,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28406.0,
"min": 16831.0,
"max": 32505.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7131414963811074,
"min": -0.9273625493515283,
"max": 1.7249902663300338,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 181.59299861639738,
"min": -29.675601579248905,
"max": 181.59299861639738,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7131414963811074,
"min": -0.9273625493515283,
"max": 1.7249902663300338,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 181.59299861639738,
"min": -29.675601579248905,
"max": 181.59299861639738,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02838465505919885,
"min": 0.02838465505919885,
"max": 10.564378727884854,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.008773436275078,
"min": 3.008773436275078,
"max": 179.5944383740425,
"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": "1729398143",
"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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729401404"
},
"total": 3260.695443254999,
"count": 1,
"self": 0.57952102499803,
"children": {
"run_training.setup": {
"total": 0.10485332400094194,
"count": 1,
"self": 0.10485332400094194
},
"TrainerController.start_learning": {
"total": 3260.011068906,
"count": 1,
"self": 2.340491514010864,
"children": {
"TrainerController._reset_env": {
"total": 2.3992441420014075,
"count": 1,
"self": 2.3992441420014075
},
"TrainerController.advance": {
"total": 3255.1886292169893,
"count": 64174,
"self": 2.430802335116823,
"children": {
"env_step": {
"total": 2174.0572805580596,
"count": 64174,
"self": 2011.3544784380792,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.325576389876,
"count": 64174,
"self": 6.851961567735998,
"children": {
"TorchPolicy.evaluate": {
"total": 154.47361482214,
"count": 62562,
"self": 154.47361482214
}
}
},
"workers": {
"total": 1.3772257301043282,
"count": 64174,
"self": 0.0,
"children": {
"worker_root": {
"total": 3252.62531536978,
"count": 64174,
"is_parallel": true,
"self": 1413.518096198537,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031364379992737668,
"count": 1,
"is_parallel": true,
"self": 0.0010893380022025667,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020470999970712,
"count": 8,
"is_parallel": true,
"self": 0.0020470999970712
}
}
},
"UnityEnvironment.step": {
"total": 0.06499546899976849,
"count": 1,
"is_parallel": true,
"self": 0.0007758289993944345,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005778110007668147,
"count": 1,
"is_parallel": true,
"self": 0.0005778110007668147
},
"communicator.exchange": {
"total": 0.061393872998451116,
"count": 1,
"is_parallel": true,
"self": 0.061393872998451116
},
"steps_from_proto": {
"total": 0.002247956001156126,
"count": 1,
"is_parallel": true,
"self": 0.0004586260038195178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017893299973366084,
"count": 8,
"is_parallel": true,
"self": 0.0017893299973366084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1839.1072191712428,
"count": 64173,
"is_parallel": true,
"self": 47.079499576173475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 30.047299836109232,
"count": 64173,
"is_parallel": true,
"self": 30.047299836109232
},
"communicator.exchange": {
"total": 1635.6801478572543,
"count": 64173,
"is_parallel": true,
"self": 1635.6801478572543
},
"steps_from_proto": {
"total": 126.30027190170586,
"count": 64173,
"is_parallel": true,
"self": 28.02582484746563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 98.27444705424023,
"count": 513384,
"is_parallel": true,
"self": 98.27444705424023
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1078.700546323813,
"count": 64174,
"self": 4.679823476959427,
"children": {
"process_trajectory": {
"total": 166.48917414384232,
"count": 64174,
"self": 166.304204434844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18496970899832377,
"count": 2,
"self": 0.18496970899832377
}
}
},
"_update_policy": {
"total": 907.5315487030111,
"count": 457,
"self": 365.3974767540658,
"children": {
"TorchPPOOptimizer.update": {
"total": 542.1340719489453,
"count": 22767,
"self": 542.1340719489453
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4799989003222436e-06,
"count": 1,
"self": 1.4799989003222436e-06
},
"TrainerController._save_models": {
"total": 0.0827025529997627,
"count": 1,
"self": 0.001807255999665358,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08089529700009734,
"count": 1,
"self": 0.08089529700009734
}
}
}
}
}
}
}