ppo-Huggy / run_logs /timers.json
TahaBa's picture
Huggy
c922490 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024502038955688,
"min": 1.4024502038955688,
"max": 1.425650954246521,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69666.7109375,
"min": 69503.1171875,
"max": 75134.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 71.87609329446065,
"min": 67.89241379310344,
"max": 404.03225806451616,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49307.0,
"min": 49194.0,
"max": 50100.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999987.0,
"min": 49474.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999987.0,
"min": 49474.0,
"max": 1999987.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5548737049102783,
"min": 0.08154536038637161,
"max": 2.5710978507995605,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1752.643310546875,
"min": 10.030078887939453,
"max": 1790.543701171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9815731088552115,
"min": 1.908796827967574,
"max": 4.090431898832321,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2731.359152674675,
"min": 234.7820098400116,
"max": 2827.137022435665,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9815731088552115,
"min": 1.908796827967574,
"max": 4.090431898832321,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2731.359152674675,
"min": 234.7820098400116,
"max": 2827.137022435665,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0178387229259695,
"min": 0.013175914688569415,
"max": 0.020153452876547816,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053516168777908504,
"min": 0.02635182937713883,
"max": 0.05642365161026343,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.056471528485417366,
"min": 0.022479511424899103,
"max": 0.06029920919487873,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1694145854562521,
"min": 0.044959022849798205,
"max": 0.17420077038307985,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.912448695883342e-06,
"min": 3.912448695883342e-06,
"max": 0.00029535435154855,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1737346087650025e-05,
"min": 1.1737346087650025e-05,
"max": 0.0008441203686265498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10130411666666668,
"min": 0.10130411666666668,
"max": 0.19845144999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30391235000000005,
"min": 0.2077386499999999,
"max": 0.5813734500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.507542166666682e-05,
"min": 7.507542166666682e-05,
"max": 0.004922727355,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022522626500000046,
"min": 0.00022522626500000046,
"max": 0.014070535155000001,
"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": "1722437176",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722439772"
},
"total": 2595.644459442,
"count": 1,
"self": 0.43768599000031827,
"children": {
"run_training.setup": {
"total": 0.06011105800007499,
"count": 1,
"self": 0.06011105800007499
},
"TrainerController.start_learning": {
"total": 2595.1466623939996,
"count": 1,
"self": 4.997727490214402,
"children": {
"TrainerController._reset_env": {
"total": 2.8092612489999738,
"count": 1,
"self": 2.8092612489999738
},
"TrainerController.advance": {
"total": 2587.216722050785,
"count": 233530,
"self": 5.137345353715773,
"children": {
"env_step": {
"total": 2044.532975199002,
"count": 233530,
"self": 1685.1527759680669,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.1216916809251,
"count": 233530,
"self": 17.879020648979804,
"children": {
"TorchPolicy.evaluate": {
"total": 338.2426710319453,
"count": 222916,
"self": 338.2426710319453
}
}
},
"workers": {
"total": 3.2585075500101084,
"count": 233530,
"self": 0.0,
"children": {
"worker_root": {
"total": 2587.3786731071223,
"count": 233530,
"is_parallel": true,
"self": 1231.1618716150133,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001025329999947644,
"count": 1,
"is_parallel": true,
"self": 0.00026673499996832106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007585949999793229,
"count": 2,
"is_parallel": true,
"self": 0.0007585949999793229
}
}
},
"UnityEnvironment.step": {
"total": 0.03022317899990412,
"count": 1,
"is_parallel": true,
"self": 0.0003978140000526764,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020858399989265308,
"count": 1,
"is_parallel": true,
"self": 0.00020858399989265308
},
"communicator.exchange": {
"total": 0.028854897999963214,
"count": 1,
"is_parallel": true,
"self": 0.028854897999963214
},
"steps_from_proto": {
"total": 0.0007618829999955778,
"count": 1,
"is_parallel": true,
"self": 0.00021195900012571656,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005499239998698613,
"count": 2,
"is_parallel": true,
"self": 0.0005499239998698613
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1356.216801492109,
"count": 233529,
"is_parallel": true,
"self": 41.27510047337478,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.82247603788915,
"count": 233529,
"is_parallel": true,
"self": 88.82247603788915
},
"communicator.exchange": {
"total": 1128.7920243838607,
"count": 233529,
"is_parallel": true,
"self": 1128.7920243838607
},
"steps_from_proto": {
"total": 97.32720059698431,
"count": 233529,
"is_parallel": true,
"self": 36.87359084482682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.45360975215749,
"count": 467058,
"is_parallel": true,
"self": 60.45360975215749
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 537.5464014980669,
"count": 233530,
"self": 7.5723040531704555,
"children": {
"process_trajectory": {
"total": 175.71301709389672,
"count": 233530,
"self": 174.39102156689728,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3219955269994443,
"count": 10,
"self": 1.3219955269994443
}
}
},
"_update_policy": {
"total": 354.2610803509997,
"count": 97,
"self": 287.60925728097754,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.65182307002215,
"count": 2910,
"self": 66.65182307002215
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.100000190490391e-06,
"count": 1,
"self": 1.100000190490391e-06
},
"TrainerController._save_models": {
"total": 0.12295050400007312,
"count": 1,
"self": 0.0018317949998163385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12111870900025679,
"count": 1,
"self": 0.12111870900025679
}
}
}
}
}
}
}