ppo-Huggy / run_logs /timers.json
heesup's picture
Huggy
3db446d verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4285579919815063,
"min": 1.4195828437805176,
"max": 1.4285579919815063,
"count": 5
},
"Huggy.Policy.Entropy.sum": {
"value": 68270.7890625,
"min": 68270.7890625,
"max": 77347.390625,
"count": 5
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 190.31800766283524,
"min": 190.31800766283524,
"max": 392.1015625,
"count": 5
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49673.0,
"min": 49553.0,
"max": 50189.0,
"count": 5
},
"Huggy.Step.mean": {
"value": 249836.0,
"min": 49660.0,
"max": 249836.0,
"count": 5
},
"Huggy.Step.sum": {
"value": 249836.0,
"min": 49660.0,
"max": 249836.0,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.2006275653839111,
"min": 0.14006608724594116,
"max": 1.2006275653839111,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 313.3638000488281,
"min": 17.788393020629883,
"max": 313.3638000488281,
"count": 5
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4439491732367156,
"min": 1.7494514952963731,
"max": 3.4439491732367156,
"count": 5
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 898.8707342147827,
"min": 222.1803399026394,
"max": 898.8707342147827,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4439491732367156,
"min": 1.7494514952963731,
"max": 3.4439491732367156,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 898.8707342147827,
"min": 222.1803399026394,
"max": 898.8707342147827,
"count": 5
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019505533616757022,
"min": 0.01520226820236227,
"max": 0.019505533616757022,
"count": 5
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.058516600850271064,
"min": 0.03040453640472454,
"max": 0.058516600850271064,
"count": 5
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.027091392709149256,
"min": 0.022221150963256754,
"max": 0.03003601251790921,
"count": 5
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.08127417812744776,
"min": 0.04444230192651351,
"max": 0.08127417812744776,
"count": 5
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00026578251140583326,
"min": 0.00026578251140583326,
"max": 0.000295290976569675,
"count": 5
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0007973475342174998,
"min": 0.0005470279676573497,
"max": 0.0008437899187367,
"count": 5
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1885941666666667,
"min": 0.1885941666666667,
"max": 0.198430325,
"count": 5
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.5657825000000001,
"min": 0.38234265,
"max": 0.5812633000000001,
"count": 5
},
"Huggy.Policy.Beta.mean": {
"value": 0.0044308489166666664,
"min": 0.0044308489166666664,
"max": 0.004921673217500001,
"count": 5
},
"Huggy.Policy.Beta.sum": {
"value": 0.013292546749999998,
"min": 0.009118898234999999,
"max": 0.014065038670000002,
"count": 5
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1759017591",
"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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1759017927"
},
"total": 335.82432345200004,
"count": 1,
"self": 0.25046890199996596,
"children": {
"run_training.setup": {
"total": 0.022188910000068063,
"count": 1,
"self": 0.022188910000068063
},
"TrainerController.start_learning": {
"total": 335.55166564,
"count": 1,
"self": 0.54147499097121,
"children": {
"TrainerController._reset_env": {
"total": 1.8028769180000381,
"count": 1,
"self": 1.8028769180000381
},
"TrainerController.advance": {
"total": 333.0276004070288,
"count": 31900,
"self": 0.5482180550031899,
"children": {
"env_step": {
"total": 274.55972813401354,
"count": 31900,
"self": 219.86683344504445,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.349848729992345,
"count": 31900,
"self": 2.0505458109987558,
"children": {
"TorchPolicy.evaluate": {
"total": 52.29930291899359,
"count": 31405,
"self": 52.29930291899359
}
}
},
"workers": {
"total": 0.34304595897674517,
"count": 31900,
"self": 0.0,
"children": {
"worker_root": {
"total": 333.8305134630134,
"count": 31900,
"is_parallel": true,
"self": 155.44515551301993,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007772960000238527,
"count": 1,
"is_parallel": true,
"self": 0.00023474900012843136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005425469998954213,
"count": 2,
"is_parallel": true,
"self": 0.0005425469998954213
}
}
},
"UnityEnvironment.step": {
"total": 0.02926061500011201,
"count": 1,
"is_parallel": true,
"self": 0.0002725100000589009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021994200005792663,
"count": 1,
"is_parallel": true,
"self": 0.00021994200005792663
},
"communicator.exchange": {
"total": 0.028066018000117765,
"count": 1,
"is_parallel": true,
"self": 0.028066018000117765
},
"steps_from_proto": {
"total": 0.0007021449998774187,
"count": 1,
"is_parallel": true,
"self": 0.00019123699985357234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005109080000238464,
"count": 2,
"is_parallel": true,
"self": 0.0005109080000238464
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 178.38535794999348,
"count": 31899,
"is_parallel": true,
"self": 5.002250489953667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 11.323774480025122,
"count": 31899,
"is_parallel": true,
"self": 11.323774480025122
},
"communicator.exchange": {
"total": 150.08501977700257,
"count": 31899,
"is_parallel": true,
"self": 150.08501977700257
},
"steps_from_proto": {
"total": 11.974313203012116,
"count": 31899,
"is_parallel": true,
"self": 4.249789113014003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.724524089998113,
"count": 63798,
"is_parallel": true,
"self": 7.724524089998113
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 57.919654218012056,
"count": 31900,
"self": 0.8376185510117011,
"children": {
"process_trajectory": {
"total": 15.558618091999733,
"count": 31900,
"self": 15.40938006999977,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14923802199996317,
"count": 1,
"self": 0.14923802199996317
}
}
},
"_update_policy": {
"total": 41.52341757500062,
"count": 13,
"self": 33.15757473300073,
"children": {
"TorchPPOOptimizer.update": {
"total": 8.365842841999893,
"count": 390,
"self": 8.365842841999893
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.244000031874748e-06,
"count": 1,
"self": 1.244000031874748e-06
},
"TrainerController._save_models": {
"total": 0.17971207999994476,
"count": 1,
"self": 0.0037936119999812945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17591846799996347,
"count": 1,
"self": 0.17591846799996347
}
}
}
}
}
}
}