ppo-Pyramids / run_logs /timers.json
salym's picture
First Push
012bdad verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.26384294033050537,
"min": 0.255442351102829,
"max": 0.2687845230102539,
"count": 6
},
"Pyramids.Policy.Entropy.sum": {
"value": 7923.73095703125,
"min": 5635.3427734375,
"max": 8063.5361328125,
"count": 6
},
"Pyramids.Step.mean": {
"value": 1379945.0,
"min": 1229982.0,
"max": 1379945.0,
"count": 6
},
"Pyramids.Step.sum": {
"value": 1379945.0,
"min": 1229982.0,
"max": 1379945.0,
"count": 6
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6900167465209961,
"min": 0.6900167465209961,
"max": 0.7682810425758362,
"count": 6
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 199.4148406982422,
"min": 136.10958862304688,
"max": 226.22634887695312,
"count": 6
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02048344351351261,
"min": 0.0123219583183527,
"max": 0.02048344351351261,
"count": 6
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.91971492767334,
"min": 2.7296502590179443,
"max": 5.91971492767334,
"count": 6
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 254.06666666666666,
"min": 237.79166666666666,
"max": 265.61739130434785,
"count": 6
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30488.0,
"min": 17428.0,
"max": 30983.0,
"count": 6
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6959149854257702,
"min": 1.6959149854257702,
"max": 1.7510285626564708,
"count": 6
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 203.50979825109243,
"min": 122.57199938595295,
"max": 211.13959824293852,
"count": 6
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6959149854257702,
"min": 1.6959149854257702,
"max": 1.7510285626564708,
"count": 6
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 203.50979825109243,
"min": 122.57199938595295,
"max": 211.13959824293852,
"count": 6
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.030077155294808713,
"min": 0.027341531194542766,
"max": 0.032141798182523676,
"count": 6
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.6092586353770457,
"min": 2.2499258727766573,
"max": 3.72520662820898,
"count": 6
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06887891884183599,
"min": 0.06729077657135869,
"max": 0.071918125936588,
"count": 6
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9643048637857039,
"min": 0.6116822602343746,
"max": 1.0322110879254371,
"count": 6
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01564624354761604,
"min": 0.012689103263255676,
"max": 0.01564624354761604,
"count": 6
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21904740966662456,
"min": 0.11420192936930108,
"max": 0.21904740966662456,
"count": 6
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5343372845051e-06,
"min": 7.5343372845051e-06,
"max": 3.851203954363492e-05,
"count": 6
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001054807219830714,
"min": 0.0001054807219830714,
"max": 0.0004666167444615001,
"count": 6
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251141326530612,
"min": 0.10251141326530612,
"max": 0.11283731746031747,
"count": 6
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4351597857142857,
"min": 1.0155358571428572,
"max": 1.6020037142857144,
"count": 6
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026089018520408157,
"min": 0.00026089018520408157,
"max": 0.0012924480142857142,
"count": 6
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036524625928571423,
"min": 0.0036524625928571423,
"max": 0.015678296150000003,
"count": 6
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011547029949724674,
"min": 0.011235922574996948,
"max": 0.012377644889056683,
"count": 6
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1616584211587906,
"min": 0.11139880120754242,
"max": 0.16964037716388702,
"count": 6
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 6
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 6
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1742427503",
"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 --resume --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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742427918"
},
"total": 414.8351439449998,
"count": 1,
"self": 0.38190717799989216,
"children": {
"run_training.setup": {
"total": 0.02437021699915931,
"count": 1,
"self": 0.02437021699915931
},
"TrainerController.start_learning": {
"total": 414.42886655000075,
"count": 1,
"self": 0.23783212609487236,
"children": {
"TrainerController._reset_env": {
"total": 2.304768451998825,
"count": 1,
"self": 2.304768451998825
},
"TrainerController.advance": {
"total": 411.7554672949045,
"count": 12532,
"self": 0.23943195585161448,
"children": {
"env_step": {
"total": 289.78269981805715,
"count": 12532,
"self": 262.9327802549851,
"children": {
"SubprocessEnvManager._take_step": {
"total": 26.707808853027018,
"count": 12532,
"self": 0.8267365119991155,
"children": {
"TorchPolicy.evaluate": {
"total": 25.881072341027902,
"count": 11949,
"self": 25.881072341027902
}
}
},
"workers": {
"total": 0.14211071004501719,
"count": 12532,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.9040247878802,
"count": 12532,
"is_parallel": true,
"self": 168.83507610180823,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002163049999580835,
"count": 1,
"is_parallel": true,
"self": 0.0006763979981769808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014866520014038542,
"count": 8,
"is_parallel": true,
"self": 0.0014866520014038542
}
}
},
"UnityEnvironment.step": {
"total": 0.04344998700071301,
"count": 1,
"is_parallel": true,
"self": 0.0004487350015551783,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005574799997702939,
"count": 1,
"is_parallel": true,
"self": 0.0005574799997702939
},
"communicator.exchange": {
"total": 0.041164281999954255,
"count": 1,
"is_parallel": true,
"self": 0.041164281999954255
},
"steps_from_proto": {
"total": 0.001279489999433281,
"count": 1,
"is_parallel": true,
"self": 0.00032011899747885764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009593710019544233,
"count": 8,
"is_parallel": true,
"self": 0.0009593710019544233
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.06894868607196,
"count": 12531,
"is_parallel": true,
"self": 4.618503196088568,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.4140282171392755,
"count": 12531,
"is_parallel": true,
"self": 3.4140282171392755
},
"communicator.exchange": {
"total": 222.1150075879541,
"count": 12531,
"is_parallel": true,
"self": 222.1150075879541
},
"steps_from_proto": {
"total": 14.921409684890023,
"count": 12531,
"is_parallel": true,
"self": 3.0471734643106174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.874236220579405,
"count": 100248,
"is_parallel": true,
"self": 11.874236220579405
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.73333552099575,
"count": 12532,
"self": 0.4883038229181693,
"children": {
"process_trajectory": {
"total": 24.228354634073185,
"count": 12532,
"self": 24.228354634073185
},
"_update_policy": {
"total": 97.0166770640044,
"count": 90,
"self": 51.85700015695329,
"children": {
"TorchPPOOptimizer.update": {
"total": 45.15967690705111,
"count": 4329,
"self": 45.15967690705111
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1330012057442218e-06,
"count": 1,
"self": 1.1330012057442218e-06
},
"TrainerController._save_models": {
"total": 0.13079754400132515,
"count": 1,
"self": 0.0018823530026566004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12891519099866855,
"count": 1,
"self": 0.12891519099866855
}
}
}
}
}
}
}