luozuolin's picture
First Push
d94c63f verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5099001526832581,
"min": 0.5099001526832581,
"max": 1.5519216060638428,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15264.37109375,
"min": 15264.37109375,
"max": 47079.09375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.1819128692150116,
"min": -0.09624376893043518,
"max": 0.1819128692150116,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 46.205867767333984,
"min": -23.0985050201416,
"max": 46.205867767333984,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00041879256605170667,
"min": -0.04421243444085121,
"max": 0.35247603058815,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.10637331008911133,
"min": -10.964683532714844,
"max": 83.53681945800781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07149027006241904,
"min": 0.06411416632230413,
"max": 0.07378103301595956,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0008637808738665,
"min": 0.4699054851651496,
"max": 1.04548023538761,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.009886369857797816,
"min": 0.00012298219695117913,
"max": 0.010278043483406435,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.13840917800916944,
"min": 0.0017217507573165077,
"max": 0.14389260876769008,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.470676081235715e-06,
"min": 7.470676081235715e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010458946513730001,
"min": 0.00010458946513730001,
"max": 0.0032574635141788995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249019285714285,
"min": 0.10249019285714285,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4348626999999998,
"min": 1.3691136000000002,
"max": 2.4442613,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002587702664285715,
"min": 0.0002587702664285715,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036227837300000006,
"min": 0.0036227837300000006,
"max": 0.10860352788999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008186819963157177,
"min": 0.008186819963157177,
"max": 0.2748454511165619,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11461548507213593,
"min": 0.11461548507213593,
"max": 1.9239182472229004,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 642.0208333333334,
"min": 618.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30817.0,
"min": 15984.0,
"max": 33264.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.8160707961457471,
"min": -1.0000000521540642,
"max": 0.8160707961457471,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 39.17139821499586,
"min": -32.000001668930054,
"max": 39.17139821499586,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.8160707961457471,
"min": -1.0000000521540642,
"max": 0.8160707961457471,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 39.17139821499586,
"min": -32.000001668930054,
"max": 39.17139821499586,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05507770336104537,
"min": 0.05507770336104537,
"max": 5.320750227198005,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.643729761330178,
"min": 2.5393117499770597,
"max": 85.13200363516808,
"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": "1765353193",
"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": "1765355823"
},
"total": 2629.6451572359997,
"count": 1,
"self": 0.5837938859999667,
"children": {
"run_training.setup": {
"total": 0.040329851000024064,
"count": 1,
"self": 0.040329851000024064
},
"TrainerController.start_learning": {
"total": 2629.0210334989997,
"count": 1,
"self": 2.0521968990010464,
"children": {
"TrainerController._reset_env": {
"total": 4.191240396000012,
"count": 1,
"self": 4.191240396000012
},
"TrainerController.advance": {
"total": 2622.7122713669987,
"count": 63329,
"self": 2.005219304056027,
"children": {
"env_step": {
"total": 1664.648743967071,
"count": 63329,
"self": 1524.4276707062986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.09460534190566,
"count": 63329,
"self": 5.697326815995893,
"children": {
"TorchPolicy.evaluate": {
"total": 133.39727852590977,
"count": 62549,
"self": 133.39727852590977
}
}
},
"workers": {
"total": 1.1264679188666378,
"count": 63329,
"self": 0.0,
"children": {
"worker_root": {
"total": 2622.753935882212,
"count": 63329,
"is_parallel": true,
"self": 1248.5374400943074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0034972319999724277,
"count": 1,
"is_parallel": true,
"self": 0.0012564260005092365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022408059994631913,
"count": 8,
"is_parallel": true,
"self": 0.0022408059994631913
}
}
},
"UnityEnvironment.step": {
"total": 0.07031085700009498,
"count": 1,
"is_parallel": true,
"self": 0.0006588999999621592,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005518749999282591,
"count": 1,
"is_parallel": true,
"self": 0.0005518749999282591
},
"communicator.exchange": {
"total": 0.06687398199983363,
"count": 1,
"is_parallel": true,
"self": 0.06687398199983363
},
"steps_from_proto": {
"total": 0.002226100000370934,
"count": 1,
"is_parallel": true,
"self": 0.0003921410007023951,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001833958999668539,
"count": 8,
"is_parallel": true,
"self": 0.001833958999668539
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1374.2164957879045,
"count": 63328,
"is_parallel": true,
"self": 39.416016974694685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 26.439381757083538,
"count": 63328,
"is_parallel": true,
"self": 26.439381757083538
},
"communicator.exchange": {
"total": 1179.7370713440878,
"count": 63328,
"is_parallel": true,
"self": 1179.7370713440878
},
"steps_from_proto": {
"total": 128.62402571203847,
"count": 63328,
"is_parallel": true,
"self": 26.618000262256828,
"children": {
"_process_rank_one_or_two_observation": {
"total": 102.00602544978165,
"count": 506624,
"is_parallel": true,
"self": 102.00602544978165
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 956.0583080958718,
"count": 63329,
"self": 3.612663925933248,
"children": {
"process_trajectory": {
"total": 139.66026857594125,
"count": 63329,
"self": 139.43092906294123,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22933951300001354,
"count": 2,
"self": 0.22933951300001354
}
}
},
"_update_policy": {
"total": 812.7853755939973,
"count": 443,
"self": 335.9813905320498,
"children": {
"TorchPPOOptimizer.update": {
"total": 476.8039850619475,
"count": 22803,
"self": 476.8039850619475
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.350005711894482e-07,
"count": 1,
"self": 9.350005711894482e-07
},
"TrainerController._save_models": {
"total": 0.06532390199936344,
"count": 1,
"self": 0.001347834999251063,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06397606700011238,
"count": 1,
"self": 0.06397606700011238
}
}
}
}
}
}
}