ppo-PyramidsRND / run_logs /timers.json
miiwater's picture
First Push
d78de8b verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5011521577835083,
"min": 0.44424155354499817,
"max": 1.609178900718689,
"count": 75
},
"Pyramids.Policy.Entropy.sum": {
"value": 5123.77978515625,
"min": 4449.5234375,
"max": 16477.9921875,
"count": 75
},
"Pyramids.Step.mean": {
"value": 749975.0,
"min": 9984.0,
"max": 749975.0,
"count": 75
},
"Pyramids.Step.sum": {
"value": 749975.0,
"min": 9984.0,
"max": 749975.0,
"count": 75
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.327169269323349,
"min": -0.0695885717868805,
"max": 0.3451611399650574,
"count": 75
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 28.463726043701172,
"min": -5.519579887390137,
"max": 30.02901840209961,
"count": 75
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.28073039650917053,
"min": -0.1326037496328354,
"max": 5.272843360900879,
"count": 75
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 24.42354393005371,
"min": -10.34309196472168,
"max": 417.7906494140625,
"count": 75
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 75
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 75
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.03919013744841019,
"min": 0.025907589830846216,
"max": 0.04140630515757948,
"count": 74
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.03919013744841019,
"min": 0.025907589830846216,
"max": 0.07669558403237413,
"count": 74
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017723554725913953,
"min": 0.0027460590572445653,
"max": 4.572622044881185,
"count": 74
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.017723554725913953,
"min": 0.0027460590572445653,
"max": 4.572622044881185,
"count": 74
},
"Pyramids.Policy.LearningRate.mean": {
"value": 4.37943245746668e-06,
"min": 4.37943245746668e-06,
"max": 0.0004931733346986669,
"count": 74
},
"Pyramids.Policy.LearningRate.sum": {
"value": 4.37943245746668e-06,
"min": 4.37943245746668e-06,
"max": 0.0009010206864625333,
"count": 74
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10087586666666669,
"min": 0.10087586666666669,
"max": 0.1986346666666667,
"count": 74
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.10087586666666669,
"min": 0.10087586666666669,
"max": 0.38020413333333336,
"count": 74
},
"Pyramids.Policy.Beta.mean": {
"value": 3.6188413333333414e-05,
"min": 3.6188413333333414e-05,
"max": 0.0029591765333333337,
"count": 74
},
"Pyramids.Policy.Beta.sum": {
"value": 3.6188413333333414e-05,
"min": 3.6188413333333414e-05,
"max": 0.005408103586666667,
"count": 74
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0742863118648529,
"min": 0.07240751385688782,
"max": 4.2070794105529785,
"count": 74
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.0742863118648529,
"min": 0.07240751385688782,
"max": 4.2070794105529785,
"count": 74
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 559.5,
"min": 424.25,
"max": 999.0,
"count": 72
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 11190.0,
"min": 774.0,
"max": 15984.0,
"count": 72
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9432475896818298,
"min": -1.0000000521540642,
"max": 1.5757499746978283,
"count": 72
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 19.808199383318424,
"min": -16.000000834465027,
"max": 31.514999493956566,
"count": 72
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9432475896818298,
"min": -1.0000000521540642,
"max": 1.5757499746978283,
"count": 72
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 19.808199383318424,
"min": -16.000000834465027,
"max": 31.514999493956566,
"count": 72
},
"Pyramids.Policy.RndReward.mean": {
"value": 1.3058350549212523,
"min": 0.9196151447120227,
"max": 234.79986264556646,
"count": 72
},
"Pyramids.Policy.RndReward.sum": {
"value": 27.4225361533463,
"min": 10.76187589764595,
"max": 3756.7978023290634,
"count": 72
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1760370346",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1760371747"
},
"total": 1400.808426334,
"count": 1,
"self": 0.5409871720000865,
"children": {
"run_training.setup": {
"total": 0.02287479999995412,
"count": 1,
"self": 0.02287479999995412
},
"TrainerController.start_learning": {
"total": 1400.244564362,
"count": 1,
"self": 0.8984181139846896,
"children": {
"TrainerController._reset_env": {
"total": 2.10195284800011,
"count": 1,
"self": 2.10195284800011
},
"TrainerController.advance": {
"total": 1397.184752896015,
"count": 47632,
"self": 0.9062883149949812,
"children": {
"env_step": {
"total": 1083.7232530879967,
"count": 47632,
"self": 980.4546420019965,
"children": {
"SubprocessEnvManager._take_step": {
"total": 102.72167011603483,
"count": 47632,
"self": 3.199262073034106,
"children": {
"TorchPolicy.evaluate": {
"total": 99.52240804300072,
"count": 46941,
"self": 99.52240804300072
}
}
},
"workers": {
"total": 0.5469409699653625,
"count": 47632,
"self": 0.0,
"children": {
"worker_root": {
"total": 1395.1777106480372,
"count": 47632,
"is_parallel": true,
"self": 495.2137214700706,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001759886999934679,
"count": 1,
"is_parallel": true,
"self": 0.0005297669999890786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012301199999456003,
"count": 8,
"is_parallel": true,
"self": 0.0012301199999456003
}
}
},
"UnityEnvironment.step": {
"total": 0.047367437000048085,
"count": 1,
"is_parallel": true,
"self": 0.0005135589999554213,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004283159998976771,
"count": 1,
"is_parallel": true,
"self": 0.0004283159998976771
},
"communicator.exchange": {
"total": 0.044788995000089926,
"count": 1,
"is_parallel": true,
"self": 0.044788995000089926
},
"steps_from_proto": {
"total": 0.0016365670001050603,
"count": 1,
"is_parallel": true,
"self": 0.00035234200049671927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001284224999608341,
"count": 8,
"is_parallel": true,
"self": 0.001284224999608341
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 899.9639891779666,
"count": 47631,
"is_parallel": true,
"self": 23.731758343956017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 16.253265209982374,
"count": 47631,
"is_parallel": true,
"self": 16.253265209982374
},
"communicator.exchange": {
"total": 785.35100354107,
"count": 47631,
"is_parallel": true,
"self": 785.35100354107
},
"steps_from_proto": {
"total": 74.62796208295822,
"count": 47631,
"is_parallel": true,
"self": 15.369049118188968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.25891296476925,
"count": 381048,
"is_parallel": true,
"self": 59.25891296476925
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 312.5552114930233,
"count": 47632,
"self": 1.7117872510218604,
"children": {
"process_trajectory": {
"total": 86.40516121200312,
"count": 47632,
"self": 86.31369699000311,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09146422200001325,
"count": 1,
"self": 0.09146422200001325
}
}
},
"_update_policy": {
"total": 224.43826302999832,
"count": 88,
"self": 171.00575451598752,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.432508514010806,
"count": 4314,
"self": 53.432508514010806
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.810002327663824e-07,
"count": 1,
"self": 8.810002327663824e-07
},
"TrainerController._save_models": {
"total": 0.05943962299988925,
"count": 1,
"self": 0.0005885860000489629,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05885103699984029,
"count": 1,
"self": 0.05885103699984029
}
}
}
}
}
}
}