ppo-Huggy / run_logs /timers.json
MLIsaac's picture
Huggy
36c2237 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4141807556152344,
"min": 1.4141807556152344,
"max": 1.429761528968811,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69786.9921875,
"min": 68236.140625,
"max": 76965.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.88023952095809,
"min": 86.64964788732394,
"max": 390.5234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49539.0,
"min": 49096.0,
"max": 49990.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49895.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49895.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3254880905151367,
"min": 0.032883889973163605,
"max": 2.449495315551758,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1165.069580078125,
"min": 4.176253795623779,
"max": 1353.14208984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5837858710698263,
"min": 1.7867480826190139,
"max": 3.9141819722711024,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1795.476721405983,
"min": 226.91700649261475,
"max": 2122.2278038859367,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5837858710698263,
"min": 1.7867480826190139,
"max": 3.9141819722711024,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1795.476721405983,
"min": 226.91700649261475,
"max": 2122.2278038859367,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017369092252839537,
"min": 0.013035111256613163,
"max": 0.019030089688021692,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05210727675851861,
"min": 0.026070222513226327,
"max": 0.05709026906406507,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.050535687224732506,
"min": 0.022985377814620733,
"max": 0.05808570974816879,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15160706167419752,
"min": 0.045970755629241467,
"max": 0.17055853543182214,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5264988245333406e-06,
"min": 3.5264988245333406e-06,
"max": 0.0002953128765623749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0579496473600022e-05,
"min": 1.0579496473600022e-05,
"max": 0.0008440455186514998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117546666666666,
"min": 0.10117546666666666,
"max": 0.198437625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035264,
"min": 0.20748795000000003,
"max": 0.5813485000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.86557866666668e-05,
"min": 6.86557866666668e-05,
"max": 0.004922037487500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002059673600000004,
"min": 0.0002059673600000004,
"max": 0.014069290150000004,
"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": "1713211266",
"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": "1713213918"
},
"total": 2652.052758793,
"count": 1,
"self": 0.49026653200007786,
"children": {
"run_training.setup": {
"total": 0.06164451100005408,
"count": 1,
"self": 0.06164451100005408
},
"TrainerController.start_learning": {
"total": 2651.50084775,
"count": 1,
"self": 4.631527033973271,
"children": {
"TrainerController._reset_env": {
"total": 3.5044251319999944,
"count": 1,
"self": 3.5044251319999944
},
"TrainerController.advance": {
"total": 2643.2304858510265,
"count": 232221,
"self": 4.768819250959041,
"children": {
"env_step": {
"total": 2091.969670422982,
"count": 232221,
"self": 1715.1414890269887,
"children": {
"SubprocessEnvManager._take_step": {
"total": 373.758839075975,
"count": 232221,
"self": 18.083167602976346,
"children": {
"TorchPolicy.evaluate": {
"total": 355.67567147299866,
"count": 223010,
"self": 355.67567147299866
}
}
},
"workers": {
"total": 3.0693423200181655,
"count": 232221,
"self": 0.0,
"children": {
"worker_root": {
"total": 2644.086284500111,
"count": 232221,
"is_parallel": true,
"self": 1258.4658953270857,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001295937000008962,
"count": 1,
"is_parallel": true,
"self": 0.00031883999997717183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009770970000317902,
"count": 2,
"is_parallel": true,
"self": 0.0009770970000317902
}
}
},
"UnityEnvironment.step": {
"total": 0.03536238899999944,
"count": 1,
"is_parallel": true,
"self": 0.00044147200003408216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025638500000013664,
"count": 1,
"is_parallel": true,
"self": 0.00025638500000013664
},
"communicator.exchange": {
"total": 0.03378639799996108,
"count": 1,
"is_parallel": true,
"self": 0.03378639799996108
},
"steps_from_proto": {
"total": 0.0008781340000041382,
"count": 1,
"is_parallel": true,
"self": 0.0002487479999899733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006293860000141649,
"count": 2,
"is_parallel": true,
"self": 0.0006293860000141649
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1385.6203891730254,
"count": 232220,
"is_parallel": true,
"self": 41.360522170115246,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.99008746789758,
"count": 232220,
"is_parallel": true,
"self": 90.99008746789758
},
"communicator.exchange": {
"total": 1156.431440894983,
"count": 232220,
"is_parallel": true,
"self": 1156.431440894983
},
"steps_from_proto": {
"total": 96.8383386400294,
"count": 232220,
"is_parallel": true,
"self": 35.231829535078816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.60650910495059,
"count": 464440,
"is_parallel": true,
"self": 61.60650910495059
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 546.4919961770854,
"count": 232221,
"self": 7.992798807108329,
"children": {
"process_trajectory": {
"total": 185.41561242497852,
"count": 232221,
"self": 183.87581883497836,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5397935900001585,
"count": 10,
"self": 1.5397935900001585
}
}
},
"_update_policy": {
"total": 353.08358494499856,
"count": 97,
"self": 279.97339751700326,
"children": {
"TorchPPOOptimizer.update": {
"total": 73.1101874279953,
"count": 2910,
"self": 73.1101874279953
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1140000424347818e-06,
"count": 1,
"self": 1.1140000424347818e-06
},
"TrainerController._save_models": {
"total": 0.13440861900016898,
"count": 1,
"self": 0.0038828690003356314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13052574999983335,
"count": 1,
"self": 0.13052574999983335
}
}
}
}
}
}
}