ppo-Huggy2 / run_logs /timers.json
Vrepol's picture
Huggy2
0ee3997 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4198955297470093,
"min": 1.4190006256103516,
"max": 1.4198955297470093,
"count": 4
},
"Huggy.Policy.Entropy.sum": {
"value": 70530.46875,
"min": 69921.890625,
"max": 78912.046875,
"count": 4
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 432.37931034482756,
"min": 399.08,
"max": 440.5,
"count": 4
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50156.0,
"min": 49648.0,
"max": 50217.0,
"count": 4
},
"Huggy.Step.mean": {
"value": 199727.0,
"min": 49976.0,
"max": 199727.0,
"count": 4
},
"Huggy.Step.sum": {
"value": 199727.0,
"min": 49976.0,
"max": 199727.0,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.258228600025177,
"min": 0.016751525923609734,
"max": 0.258228600025177,
"count": 4
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 29.954519271850586,
"min": 1.8929224014282227,
"max": 29.954519271850586,
"count": 4
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 1.933929322608586,
"min": 1.73765958384075,
"max": 1.933929322608586,
"count": 4
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 224.33580142259598,
"min": 196.35553297400475,
"max": 224.33580142259598,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 1.933929322608586,
"min": 1.73765958384075,
"max": 1.933929322608586,
"count": 4
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 224.33580142259598,
"min": 196.35553297400475,
"max": 224.33580142259598,
"count": 4
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014423672328121029,
"min": 0.010845656427166735,
"max": 0.014423672328121029,
"count": 4
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.014423672328121029,
"min": 0.010845656427166735,
"max": 0.014423672328121029,
"count": 4
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.022282263139883678,
"min": 0.022282263139883678,
"max": 0.029831122110287347,
"count": 4
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.022282263139883678,
"min": 0.022282263139883678,
"max": 0.029831122110287347,
"count": 4
},
"Huggy.Policy.LearningRate.mean": {
"value": 1.7653582346499997e-05,
"min": 1.7653582346499997e-05,
"max": 7.950802049199998e-05,
"count": 4
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.7653582346499997e-05,
"min": 1.7653582346499997e-05,
"max": 7.950802049199998e-05,
"count": 4
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.11765349999999998,
"min": 0.11765349999999998,
"max": 0.17950800000000006,
"count": 4
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.11765349999999998,
"min": 0.11765349999999998,
"max": 0.17950800000000006,
"count": 4
},
"Huggy.Policy.Beta.mean": {
"value": 0.0008909096500000002,
"min": 0.0008909096500000002,
"max": 0.003977449199999999,
"count": 4
},
"Huggy.Policy.Beta.sum": {
"value": 0.0008909096500000002,
"min": 0.0008909096500000002,
"max": 0.003977449199999999,
"count": 4
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1728461087",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=Huggy3 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728461329"
},
"total": 242.4948682040001,
"count": 1,
"self": 0.4359311760001674,
"children": {
"run_training.setup": {
"total": 0.054265040000018416,
"count": 1,
"self": 0.054265040000018416
},
"TrainerController.start_learning": {
"total": 242.00467198799993,
"count": 1,
"self": 0.4254221500177664,
"children": {
"TrainerController._reset_env": {
"total": 1.655714339999804,
"count": 1,
"self": 1.655714339999804
},
"TrainerController.advance": {
"total": 239.76698765798233,
"count": 23076,
"self": 0.44474585900798047,
"children": {
"env_step": {
"total": 201.26128057799247,
"count": 23076,
"self": 150.5386662429912,
"children": {
"SubprocessEnvManager._take_step": {
"total": 50.467846079998026,
"count": 23076,
"self": 1.4970562630041968,
"children": {
"TorchPolicy.evaluate": {
"total": 48.97078981699383,
"count": 22832,
"self": 48.97078981699383
}
}
},
"workers": {
"total": 0.25476825500322775,
"count": 23076,
"self": 0.0,
"children": {
"worker_root": {
"total": 240.97939377196894,
"count": 23076,
"is_parallel": true,
"self": 118.51524733399174,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008796970000730653,
"count": 1,
"is_parallel": true,
"self": 0.00025295799991909007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006267390001539752,
"count": 2,
"is_parallel": true,
"self": 0.0006267390001539752
}
}
},
"UnityEnvironment.step": {
"total": 0.02858458400010022,
"count": 1,
"is_parallel": true,
"self": 0.0003688990000227932,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023151499999585212,
"count": 1,
"is_parallel": true,
"self": 0.00023151499999585212
},
"communicator.exchange": {
"total": 0.0272405069999877,
"count": 1,
"is_parallel": true,
"self": 0.0272405069999877
},
"steps_from_proto": {
"total": 0.0007436630000938749,
"count": 1,
"is_parallel": true,
"self": 0.00019647000021905114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005471929998748237,
"count": 2,
"is_parallel": true,
"self": 0.0005471929998748237
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 122.4641464379772,
"count": 23075,
"is_parallel": true,
"self": 3.77207202793943,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.21379293703103,
"count": 23075,
"is_parallel": true,
"self": 8.21379293703103
},
"communicator.exchange": {
"total": 101.7450849229931,
"count": 23075,
"is_parallel": true,
"self": 101.7450849229931
},
"steps_from_proto": {
"total": 8.733196550013645,
"count": 23075,
"is_parallel": true,
"self": 3.111274706048789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.621921843964856,
"count": 46150,
"is_parallel": true,
"self": 5.621921843964856
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 38.06096122098188,
"count": 23076,
"self": 0.6591138119863444,
"children": {
"process_trajectory": {
"total": 10.368716986995878,
"count": 23076,
"self": 10.205049650995761,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16366733600011685,
"count": 1,
"self": 0.16366733600011685
}
}
},
"_update_policy": {
"total": 27.033130421999658,
"count": 4,
"self": 21.540212118999307,
"children": {
"TorchPPOOptimizer.update": {
"total": 5.492918303000351,
"count": 120,
"self": 5.492918303000351
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2279999737074832e-06,
"count": 1,
"self": 1.2279999737074832e-06
},
"TrainerController._save_models": {
"total": 0.15654661200005648,
"count": 1,
"self": 0.0016006250000373257,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15494598700001916,
"count": 1,
"self": 0.15494598700001916
}
}
}
}
}
}
}