BMukhtar's picture
First Push
9334081 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5263477563858032,
"min": 0.5218650102615356,
"max": 1.4859470129013062,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15706.2177734375,
"min": 15671.2587890625,
"max": 45077.6875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989929.0,
"min": 29948.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989929.0,
"min": 29948.0,
"max": 989929.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5260055661201477,
"min": -0.08635862916707993,
"max": 0.5471867918968201,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 146.22955322265625,
"min": -20.898788452148438,
"max": 148.83480834960938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.025161098688840866,
"min": -0.008283705450594425,
"max": 0.3367824852466583,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.994785308837891,
"min": -2.269735336303711,
"max": 79.81745147705078,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0692049300589133,
"min": 0.06428446322873546,
"max": 0.07652594513801857,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0380739508836996,
"min": 0.53568161596613,
"max": 1.076596317560567,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015227047167071659,
"min": 0.001263315361502793,
"max": 0.01602631827630657,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2284057075060749,
"min": 0.0156639537060793,
"max": 0.2284057075060749,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.506677497806668e-06,
"min": 7.506677497806668e-06,
"max": 0.0002952330873032572,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011260016246710002,
"min": 0.00011260016246710002,
"max": 0.003509349530216899,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250219333333335,
"min": 0.10250219333333335,
"max": 0.1984110285714286,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375329000000002,
"min": 1.3888772,
"max": 2.5697831,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000259969114,
"min": 0.000259969114,
"max": 0.009841261754285712,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00389953671,
"min": 0.00389953671,
"max": 0.11700133168999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008508678525686264,
"min": 0.008508678525686264,
"max": 0.3853279650211334,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12763017416000366,
"min": 0.12015614658594131,
"max": 2.697295665740967,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 363.7926829268293,
"min": 351.53846153846155,
"max": 990.84375,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29831.0,
"min": 16747.0,
"max": 32690.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5590715790972298,
"min": -0.9292500528972596,
"max": 1.5616784658801706,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 126.28479790687561,
"min": -29.736001692712307,
"max": 142.00799894332886,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5590715790972298,
"min": -0.9292500528972596,
"max": 1.5616784658801706,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 126.28479790687561,
"min": -29.736001692712307,
"max": 142.00799894332886,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0320376192908885,
"min": 0.03147579691050431,
"max": 7.455379055703387,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5950471625619684,
"min": 2.5950471625619684,
"max": 126.74144394695759,
"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": "1723458959",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723461108"
},
"total": 2149.475872199,
"count": 1,
"self": 1.044809658000304,
"children": {
"run_training.setup": {
"total": 0.052715356000135216,
"count": 1,
"self": 0.052715356000135216
},
"TrainerController.start_learning": {
"total": 2148.3783471849997,
"count": 1,
"self": 1.2281253970390935,
"children": {
"TrainerController._reset_env": {
"total": 2.083797042000242,
"count": 1,
"self": 2.083797042000242
},
"TrainerController.advance": {
"total": 2144.9376074979605,
"count": 63851,
"self": 1.3423061528960716,
"children": {
"env_step": {
"total": 1521.9825932751146,
"count": 63851,
"self": 1393.3411354790696,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.86738128503384,
"count": 63851,
"self": 4.596077160103505,
"children": {
"TorchPolicy.evaluate": {
"total": 123.27130412493034,
"count": 62571,
"self": 123.27130412493034
}
}
},
"workers": {
"total": 0.774076511011117,
"count": 63851,
"self": 0.0,
"children": {
"worker_root": {
"total": 2143.6376590869213,
"count": 63851,
"is_parallel": true,
"self": 867.437833379849,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002185606000239204,
"count": 1,
"is_parallel": true,
"self": 0.0007173540002440859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014682519999951182,
"count": 8,
"is_parallel": true,
"self": 0.0014682519999951182
}
}
},
"UnityEnvironment.step": {
"total": 0.05044651099979092,
"count": 1,
"is_parallel": true,
"self": 0.0006356289991344966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004845420003221079,
"count": 1,
"is_parallel": true,
"self": 0.0004845420003221079
},
"communicator.exchange": {
"total": 0.04754785400018591,
"count": 1,
"is_parallel": true,
"self": 0.04754785400018591
},
"steps_from_proto": {
"total": 0.0017784860001484049,
"count": 1,
"is_parallel": true,
"self": 0.0003802210003414075,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013982649998069974,
"count": 8,
"is_parallel": true,
"self": 0.0013982649998069974
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1276.1998257070723,
"count": 63850,
"is_parallel": true,
"self": 33.18240516001015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.361832671914726,
"count": 63850,
"is_parallel": true,
"self": 23.361832671914726
},
"communicator.exchange": {
"total": 1120.7273679300774,
"count": 63850,
"is_parallel": true,
"self": 1120.7273679300774
},
"steps_from_proto": {
"total": 98.92821994506994,
"count": 63850,
"is_parallel": true,
"self": 19.970993225952043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.9572267191179,
"count": 510800,
"is_parallel": true,
"self": 78.9572267191179
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 621.6127080699498,
"count": 63851,
"self": 2.5613466528880053,
"children": {
"process_trajectory": {
"total": 125.04631966406214,
"count": 63851,
"self": 124.7529433500622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2933763139999428,
"count": 2,
"self": 0.2933763139999428
}
}
},
"_update_policy": {
"total": 494.00504175299966,
"count": 454,
"self": 294.4348258650798,
"children": {
"TorchPPOOptimizer.update": {
"total": 199.57021588791986,
"count": 22779,
"self": 199.57021588791986
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3119997674948536e-06,
"count": 1,
"self": 1.3119997674948536e-06
},
"TrainerController._save_models": {
"total": 0.1288159360001373,
"count": 1,
"self": 0.0020288499999878695,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12678708600014943,
"count": 1,
"self": 0.12678708600014943
}
}
}
}
}
}
}