huanvo88's picture
Initial Model
75f9d68
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.31703633069992065,
"min": 0.2942402958869934,
"max": 1.3798967599868774,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9516.162109375,
"min": 8836.625,
"max": 41860.546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989887.0,
"min": 29952.0,
"max": 989887.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6573259830474854,
"min": -0.0974295437335968,
"max": 0.6978509426116943,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 188.65255737304688,
"min": -23.57794952392578,
"max": 204.8550567626953,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009424268268048763,
"min": -0.01474218349903822,
"max": 0.32284414768218994,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.7047650814056396,
"min": -3.9361629486083984,
"max": 78.12828063964844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06638287874385428,
"min": 0.06460588092159016,
"max": 0.0717851239079166,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9293603024139598,
"min": 0.469201992338138,
"max": 1.0457411700820862,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015603917892697022,
"min": 0.0006251493278582881,
"max": 0.0179225476911395,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2184548504977583,
"min": 0.007501791934299457,
"max": 0.2688382153670925,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4873475042499965e-06,
"min": 7.4873475042499965e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010482286505949995,
"min": 0.00010482286505949995,
"max": 0.0036330049889984005,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249575,
"min": 0.10249575,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4349405,
"min": 1.3886848,
"max": 2.6110016,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002593254249999999,
"min": 0.0002593254249999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003630555949999999,
"min": 0.003630555949999999,
"max": 0.12111905984,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012812924571335316,
"min": 0.012812924571335316,
"max": 0.4965657591819763,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17938093841075897,
"min": 0.17938093841075897,
"max": 3.4759602546691895,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 272.4952380952381,
"min": 259.10655737704917,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28612.0,
"min": 15984.0,
"max": 32508.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7248301764704146,
"min": -1.0000000521540642,
"max": 1.7248301764704146,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 182.83199870586395,
"min": -30.38160164654255,
"max": 210.38799848407507,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7248301764704146,
"min": -1.0000000521540642,
"max": 1.7248301764704146,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 182.83199870586395,
"min": -30.38160164654255,
"max": 210.38799848407507,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03651538235574679,
"min": 0.03651538235574679,
"max": 9.330626089125872,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8706305297091603,
"min": 3.8706305297091603,
"max": 149.29001742601395,
"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": "1684327600",
"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": "1684329911"
},
"total": 2310.390994325,
"count": 1,
"self": 0.8358678419999706,
"children": {
"run_training.setup": {
"total": 0.03734993399984887,
"count": 1,
"self": 0.03734993399984887
},
"TrainerController.start_learning": {
"total": 2309.5177765490002,
"count": 1,
"self": 1.3301288030183969,
"children": {
"TrainerController._reset_env": {
"total": 4.541629476999788,
"count": 1,
"self": 4.541629476999788
},
"TrainerController.advance": {
"total": 2303.5086978579825,
"count": 64244,
"self": 1.2995396469486877,
"children": {
"env_step": {
"total": 1671.6448369760114,
"count": 64244,
"self": 1565.6336120050855,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.26212248298907,
"count": 64244,
"self": 4.640548565875179,
"children": {
"TorchPolicy.evaluate": {
"total": 100.62157391711389,
"count": 62548,
"self": 100.62157391711389
}
}
},
"workers": {
"total": 0.7491024879368524,
"count": 64244,
"self": 0.0,
"children": {
"worker_root": {
"total": 2304.2577391889618,
"count": 64244,
"is_parallel": true,
"self": 850.642521969899,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017477589999543852,
"count": 1,
"is_parallel": true,
"self": 0.0005361979983717902,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001211561001582595,
"count": 8,
"is_parallel": true,
"self": 0.001211561001582595
}
}
},
"UnityEnvironment.step": {
"total": 0.054220794000229944,
"count": 1,
"is_parallel": true,
"self": 0.0005681020002157311,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005641849998028192,
"count": 1,
"is_parallel": true,
"self": 0.0005641849998028192
},
"communicator.exchange": {
"total": 0.050768432000040775,
"count": 1,
"is_parallel": true,
"self": 0.050768432000040775
},
"steps_from_proto": {
"total": 0.0023200750001706183,
"count": 1,
"is_parallel": true,
"self": 0.0005151800000930962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018048950000775221,
"count": 8,
"is_parallel": true,
"self": 0.0018048950000775221
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1453.6152172190627,
"count": 64243,
"is_parallel": true,
"self": 31.937595679011338,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.843816897060606,
"count": 64243,
"is_parallel": true,
"self": 22.843816897060606
},
"communicator.exchange": {
"total": 1300.3793820959004,
"count": 64243,
"is_parallel": true,
"self": 1300.3793820959004
},
"steps_from_proto": {
"total": 98.45442254709042,
"count": 64243,
"is_parallel": true,
"self": 19.817168764840062,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.63725378225035,
"count": 513944,
"is_parallel": true,
"self": 78.63725378225035
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 630.5643212350224,
"count": 64244,
"self": 2.533189887034041,
"children": {
"process_trajectory": {
"total": 107.57285809398309,
"count": 64244,
"self": 107.2620956179835,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3107624759995815,
"count": 2,
"self": 0.3107624759995815
}
}
},
"_update_policy": {
"total": 520.4582732540052,
"count": 455,
"self": 334.80180891902774,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.6564643349775,
"count": 22803,
"self": 185.6564643349775
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.297999915550463e-06,
"count": 1,
"self": 1.297999915550463e-06
},
"TrainerController._save_models": {
"total": 0.1373191129996485,
"count": 1,
"self": 0.0017979439990085666,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13552116900063993,
"count": 1,
"self": 0.13552116900063993
}
}
}
}
}
}
}