ppo-Huggy / run_logs /timers.json
vkublytskyi's picture
Huggy
b0293de verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4085420370101929,
"min": 1.4085420370101929,
"max": 1.4268522262573242,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69477.7421875,
"min": 69279.984375,
"max": 77143.75,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 78.86900958466454,
"min": 74.73939393939393,
"max": 430.58620689655174,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49372.0,
"min": 49161.0,
"max": 50280.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49638.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49638.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4527807235717773,
"min": -0.02143266424536705,
"max": 2.497119665145874,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1535.4407958984375,
"min": -2.464756488800049,
"max": 1603.635986328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.876111568067782,
"min": 1.686557850630387,
"max": 4.017897262626531,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2426.4458416104317,
"min": 193.9541528224945,
"max": 2503.988489329815,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.876111568067782,
"min": 1.686557850630387,
"max": 4.017897262626531,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2426.4458416104317,
"min": 193.9541528224945,
"max": 2503.988489329815,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015411516581176935,
"min": 0.01362504788072935,
"max": 0.018689241657799963,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046234549743530806,
"min": 0.0272500957614587,
"max": 0.054909866140345306,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06144184594353041,
"min": 0.022153666636182203,
"max": 0.06144184594353041,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18432553783059122,
"min": 0.04553500295927127,
"max": 0.18432553783059122,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.84414871865e-06,
"min": 3.84414871865e-06,
"max": 0.00029534287655237504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1532446155949998e-05,
"min": 1.1532446155949998e-05,
"max": 0.0008443785185404998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128135,
"min": 0.10128135,
"max": 0.19844762500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30384405000000003,
"min": 0.20769280000000007,
"max": 0.5814595,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.393936499999998e-05,
"min": 7.393936499999998e-05,
"max": 0.0049225364875,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022181809499999993,
"min": 0.00022181809499999993,
"max": 0.014074829050000005,
"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": "1745442026",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745444460"
},
"total": 2434.24216452,
"count": 1,
"self": 0.44502186799945775,
"children": {
"run_training.setup": {
"total": 0.02307514800008903,
"count": 1,
"self": 0.02307514800008903
},
"TrainerController.start_learning": {
"total": 2433.7740675040004,
"count": 1,
"self": 4.302831680999134,
"children": {
"TrainerController._reset_env": {
"total": 3.5781510110000454,
"count": 1,
"self": 3.5781510110000454
},
"TrainerController.advance": {
"total": 2425.7903482640013,
"count": 232898,
"self": 4.462300314135973,
"children": {
"env_step": {
"total": 1936.1123140599977,
"count": 232898,
"self": 1522.9038888340613,
"children": {
"SubprocessEnvManager._take_step": {
"total": 410.63137568603406,
"count": 232898,
"self": 15.746364865004352,
"children": {
"TorchPolicy.evaluate": {
"total": 394.8850108210297,
"count": 222878,
"self": 394.8850108210297
}
}
},
"workers": {
"total": 2.5770495399024185,
"count": 232898,
"self": 0.0,
"children": {
"worker_root": {
"total": 2426.430255217908,
"count": 232898,
"is_parallel": true,
"self": 1183.2046481869236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009265720000257716,
"count": 1,
"is_parallel": true,
"self": 0.00026335800021115574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006632139998146158,
"count": 2,
"is_parallel": true,
"self": 0.0006632139998146158
}
}
},
"UnityEnvironment.step": {
"total": 0.05032344000005651,
"count": 1,
"is_parallel": true,
"self": 0.00033072200062633783,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020844399978159345,
"count": 1,
"is_parallel": true,
"self": 0.00020844399978159345
},
"communicator.exchange": {
"total": 0.04904697399979341,
"count": 1,
"is_parallel": true,
"self": 0.04904697399979341
},
"steps_from_proto": {
"total": 0.0007372999998551677,
"count": 1,
"is_parallel": true,
"self": 0.00020728499998767802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005300149998674897,
"count": 2,
"is_parallel": true,
"self": 0.0005300149998674897
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1243.2256070309843,
"count": 232897,
"is_parallel": true,
"self": 37.47586894992787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.57101775309593,
"count": 232897,
"is_parallel": true,
"self": 82.57101775309593
},
"communicator.exchange": {
"total": 1034.6217214299543,
"count": 232897,
"is_parallel": true,
"self": 1034.6217214299543
},
"steps_from_proto": {
"total": 88.55699889800621,
"count": 232897,
"is_parallel": true,
"self": 32.58219086795225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.974808030053964,
"count": 465794,
"is_parallel": true,
"self": 55.974808030053964
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 485.2157338898678,
"count": 232898,
"self": 6.478455441900678,
"children": {
"process_trajectory": {
"total": 162.5960834039695,
"count": 232898,
"self": 161.39776849996974,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1983149039997443,
"count": 10,
"self": 1.1983149039997443
}
}
},
"_update_policy": {
"total": 316.14119504399764,
"count": 97,
"self": 251.97502604498732,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.16616899901032,
"count": 2910,
"self": 64.16616899901032
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.000000318337698e-07,
"count": 1,
"self": 9.000000318337698e-07
},
"TrainerController._save_models": {
"total": 0.10273564799990709,
"count": 1,
"self": 0.0015235769997161697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10121207100019092,
"count": 1,
"self": 0.10121207100019092
}
}
}
}
}
}
}