ppo-Huggy / run_logs /timers.json
RealBatelier's picture
Huggy
6bb6d37 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403009057044983,
"min": 1.403009057044983,
"max": 1.4272940158843994,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70417.0234375,
"min": 68067.78125,
"max": 77018.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 112.34389140271493,
"min": 92.4438202247191,
"max": 384.7,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49656.0,
"min": 48993.0,
"max": 50114.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999996.0,
"min": 49966.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999996.0,
"min": 49966.0,
"max": 1999996.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3370509147644043,
"min": 0.04984726756811142,
"max": 2.4356701374053955,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1030.639404296875,
"min": 6.430297374725342,
"max": 1253.9215087890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.568106578185715,
"min": 1.790509580410728,
"max": 3.8801819670066404,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1573.5350009799004,
"min": 230.97573587298393,
"max": 1983.7882163524628,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.568106578185715,
"min": 1.790509580410728,
"max": 3.8801819670066404,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1573.5350009799004,
"min": 230.97573587298393,
"max": 1983.7882163524628,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019335052070285505,
"min": 0.012637451958532135,
"max": 0.019961806093730654,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03867010414057101,
"min": 0.02527490391706427,
"max": 0.054703833103728054,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04703333955258131,
"min": 0.022690573893487453,
"max": 0.0597368692772256,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09406667910516261,
"min": 0.045381147786974906,
"max": 0.1792106078316768,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.378748540449996e-06,
"min": 4.378748540449996e-06,
"max": 0.00029538532653822496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.757497080899992e-06,
"min": 8.757497080899992e-06,
"max": 0.0008442079685973497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10145955000000004,
"min": 0.10145955000000004,
"max": 0.19846177499999995,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20291910000000007,
"min": 0.20291910000000007,
"max": 0.58140265,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.283154499999994e-05,
"min": 8.283154499999994e-05,
"max": 0.0049232425725,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001656630899999999,
"min": 0.0001656630899999999,
"max": 0.014071992234999997,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1715089356",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715091968"
},
"total": 2612.0024181420004,
"count": 1,
"self": 0.44341679800027123,
"children": {
"run_training.setup": {
"total": 0.0572851609999816,
"count": 1,
"self": 0.0572851609999816
},
"TrainerController.start_learning": {
"total": 2611.501716183,
"count": 1,
"self": 4.960617996993278,
"children": {
"TrainerController._reset_env": {
"total": 2.8374284679999846,
"count": 1,
"self": 2.8374284679999846
},
"TrainerController.advance": {
"total": 2603.574931975007,
"count": 231825,
"self": 5.181864304222017,
"children": {
"env_step": {
"total": 2101.28315158589,
"count": 231825,
"self": 1745.0036693436477,
"children": {
"SubprocessEnvManager._take_step": {
"total": 353.0084229021876,
"count": 231825,
"self": 18.5085364102099,
"children": {
"TorchPolicy.evaluate": {
"total": 334.4998864919777,
"count": 223029,
"self": 334.4998864919777
}
}
},
"workers": {
"total": 3.271059340054876,
"count": 231825,
"self": 0.0,
"children": {
"worker_root": {
"total": 2603.531707258078,
"count": 231825,
"is_parallel": true,
"self": 1197.7870796271236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010199480000210315,
"count": 1,
"is_parallel": true,
"self": 0.00029788200004077225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007220659999802592,
"count": 2,
"is_parallel": true,
"self": 0.0007220659999802592
}
}
},
"UnityEnvironment.step": {
"total": 0.029673661999936485,
"count": 1,
"is_parallel": true,
"self": 0.0003900719999592184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019572000007883616,
"count": 1,
"is_parallel": true,
"self": 0.00019572000007883616
},
"communicator.exchange": {
"total": 0.028229241999952137,
"count": 1,
"is_parallel": true,
"self": 0.028229241999952137
},
"steps_from_proto": {
"total": 0.0008586279999462931,
"count": 1,
"is_parallel": true,
"self": 0.00024071099994671386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006179169999995793,
"count": 2,
"is_parallel": true,
"self": 0.0006179169999995793
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1405.7446276309543,
"count": 231824,
"is_parallel": true,
"self": 41.5637678510202,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.28450633305738,
"count": 231824,
"is_parallel": true,
"self": 93.28450633305738
},
"communicator.exchange": {
"total": 1171.7641442639474,
"count": 231824,
"is_parallel": true,
"self": 1171.7641442639474
},
"steps_from_proto": {
"total": 99.13220918292927,
"count": 231824,
"is_parallel": true,
"self": 37.401269296846976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.7309398860823,
"count": 463648,
"is_parallel": true,
"self": 61.7309398860823
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.10991608489473,
"count": 231825,
"self": 7.412953547837901,
"children": {
"process_trajectory": {
"total": 161.74889032005683,
"count": 231825,
"self": 160.43791516205567,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3109751580011562,
"count": 10,
"self": 1.3109751580011562
}
}
},
"_update_policy": {
"total": 327.948072217,
"count": 96,
"self": 264.6564507940177,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.2916214229823,
"count": 2880,
"self": 63.2916214229823
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.260002116207033e-07,
"count": 1,
"self": 9.260002116207033e-07
},
"TrainerController._save_models": {
"total": 0.12873681699966255,
"count": 1,
"self": 0.002047181999841996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12668963499982056,
"count": 1,
"self": 0.12668963499982056
}
}
}
}
}
}
}