d-ch's picture
Pyramids training with ML-Agents-Pyramids
694ef45 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.20901630818843842,
"min": 0.20901630818843842,
"max": 1.5774061679840088,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 6160.12841796875,
"min": 6160.12841796875,
"max": 50476.99609375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989825.0,
"min": 29912.0,
"max": 989825.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989825.0,
"min": 29912.0,
"max": 989825.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5118342041969299,
"min": -0.09061796218156815,
"max": 0.5367960333824158,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 76.77513122558594,
"min": -11.055391311645508,
"max": 83.74018096923828,
"count": 33
},
"Pyramids.Policy.CuriosityValueEstimate.mean": {
"value": 0.3311683237552643,
"min": 0.20581792294979095,
"max": 1.2215547561645508,
"count": 33
},
"Pyramids.Policy.CuriosityValueEstimate.sum": {
"value": 49.67524719238281,
"min": 24.492332458496094,
"max": 149.02967834472656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.049747919217813484,
"min": 0.04635963973212237,
"max": 0.05792229417723623,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.3482354345246944,
"min": 0.1611601182734982,
"max": 0.4026709842728451,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012395709054483426,
"min": 0.0019444018430597333,
"max": 0.012583779305194704,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.08676996338138399,
"min": 0.0116664110583584,
"max": 0.09824015149933985,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.758525985285716e-06,
"min": 7.758525985285716e-06,
"max": 0.00029516160161279994,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 5.430968189700001e-05,
"min": 5.430968189700001e-05,
"max": 0.0020758198080600998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10258614285714288,
"min": 0.10258614285714288,
"max": 0.19838719999999999,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.7181030000000002,
"min": 0.5951616,
"max": 1.4919399000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00013904852857142858,
"min": 0.00013904852857142858,
"max": 0.004919521280000001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0009733397000000001,
"min": 0.0009733397000000001,
"max": 0.03460780101,
"count": 33
},
"Pyramids.Losses.CuriosityForwardLoss.mean": {
"value": 0.054354372236216364,
"min": 0.05257584759134001,
"max": 0.5326105538885005,
"count": 33
},
"Pyramids.Losses.CuriosityForwardLoss.sum": {
"value": 0.38048060565351455,
"min": 0.36803093313938007,
"max": 1.5978316616655017,
"count": 33
},
"Pyramids.Losses.CuriosityInverseLoss.mean": {
"value": 0.03996939331433978,
"min": 0.03854993084054773,
"max": 0.8359324191489982,
"count": 33
},
"Pyramids.Losses.CuriosityInverseLoss.sum": {
"value": 0.27978575320037846,
"min": 0.2698495158838341,
"max": 2.6150448892576,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 414.6901408450704,
"min": 384.95238095238096,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29443.0,
"min": 16293.0,
"max": 33067.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3880563101298373,
"min": -1.0000000596046448,
"max": 1.4582386761903763,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 98.55199801921844,
"min": -27.098002046346664,
"max": 118.06599801778793,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3880563101298373,
"min": -1.0000000596046448,
"max": 1.4582386761903763,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 98.55199801921844,
"min": -27.098002046346664,
"max": 118.06599801778793,
"count": 33
},
"Pyramids.Policy.CuriosityReward.mean": {
"value": 1.1747344909104662,
"min": 1.0789901474375783,
"max": 15.33528760763315,
"count": 33
},
"Pyramids.Policy.CuriosityReward.sum": {
"value": 83.4061488546431,
"min": 83.4061488546431,
"max": 432.13316164910793,
"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": "1764950447",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids.x86_64 --run-id=Pyramids1 --no-graphics --num-envs=1",
"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": "1764952290"
},
"total": 1842.8426636839995,
"count": 1,
"self": 0.33037719999992987,
"children": {
"run_training.setup": {
"total": 0.025283717999627697,
"count": 1,
"self": 0.025283717999627697
},
"TrainerController.start_learning": {
"total": 1842.487002766,
"count": 1,
"self": 1.0576689470235578,
"children": {
"TrainerController._reset_env": {
"total": 2.1140400419999423,
"count": 1,
"self": 2.1140400419999423
},
"TrainerController.advance": {
"total": 1839.1822291049766,
"count": 63901,
"self": 1.166796027104283,
"children": {
"env_step": {
"total": 1162.8995705649259,
"count": 63901,
"self": 999.4858955599047,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.70436218206942,
"count": 63901,
"self": 4.174281117070677,
"children": {
"TorchPolicy.evaluate": {
"total": 158.53008106499874,
"count": 62597,
"self": 158.53008106499874
}
}
},
"workers": {
"total": 0.7093128229516878,
"count": 63901,
"self": 0.0,
"children": {
"worker_root": {
"total": 1840.1844485941865,
"count": 63901,
"is_parallel": true,
"self": 928.329519444238,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019504570000208332,
"count": 1,
"is_parallel": true,
"self": 0.0006229280006664339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013275289993543993,
"count": 8,
"is_parallel": true,
"self": 0.0013275289993543993
}
}
},
"UnityEnvironment.step": {
"total": 0.04071113999998488,
"count": 1,
"is_parallel": true,
"self": 0.0003678319999380619,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00028838799971708795,
"count": 1,
"is_parallel": true,
"self": 0.00028838799971708795
},
"communicator.exchange": {
"total": 0.0390953800006173,
"count": 1,
"is_parallel": true,
"self": 0.0390953800006173
},
"steps_from_proto": {
"total": 0.0009595399997124332,
"count": 1,
"is_parallel": true,
"self": 0.0002228439998361864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007366959998762468,
"count": 8,
"is_parallel": true,
"self": 0.0007366959998762468
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 911.8549291499485,
"count": 63900,
"is_parallel": true,
"self": 20.815148295267136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.223226490875277,
"count": 63900,
"is_parallel": true,
"self": 14.223226490875277
},
"communicator.exchange": {
"total": 816.0747995419752,
"count": 63900,
"is_parallel": true,
"self": 816.0747995419752
},
"steps_from_proto": {
"total": 60.74175482183091,
"count": 63900,
"is_parallel": true,
"self": 12.481249607948484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 48.260505213882425,
"count": 511200,
"is_parallel": true,
"self": 48.260505213882425
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 675.1158625129465,
"count": 63901,
"self": 2.327971286803404,
"children": {
"process_trajectory": {
"total": 107.86268345913686,
"count": 63901,
"self": 107.58077212913668,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28191133000018453,
"count": 2,
"self": 0.28191133000018453
}
}
},
"_update_policy": {
"total": 564.9252077670062,
"count": 228,
"self": 384.0698609819465,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.85534678505974,
"count": 15168,
"self": 180.85534678505974
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.619999789516442e-07,
"count": 1,
"self": 8.619999789516442e-07
},
"TrainerController._save_models": {
"total": 0.13306380999983958,
"count": 1,
"self": 0.0014513899996018154,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13161242000023776,
"count": 1,
"self": 0.13161242000023776
}
}
}
}
}
}
}