kalmi901's picture
First Push
85034b1 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8619441390037537,
"min": 0.8619441390037537,
"max": 2.8516571521759033,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8220.361328125,
"min": 8220.361328125,
"max": 29235.189453125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.290427207946777,
"min": 0.6305676698684692,
"max": 13.290427207946777,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2591.63330078125,
"min": 122.33012390136719,
"max": 2694.414306640625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06588000833300398,
"min": 0.06473739288308292,
"max": 0.0748750726102919,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2635200333320159,
"min": 0.25894957153233167,
"max": 0.36120528270240515,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19148161360884416,
"min": 0.1495115998255,
"max": 0.26746021234019496,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7659264544353767,
"min": 0.598046399302,
"max": 1.3373010617009748,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.931818181818183,
"min": 4.318181818181818,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 190.0,
"max": 1440.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 4.318181818181818,
"max": 26.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 190.0,
"max": 1440.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1726853900",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726854507"
},
"total": 606.3211493260001,
"count": 1,
"self": 0.4336520009999276,
"children": {
"run_training.setup": {
"total": 0.05304578999994192,
"count": 1,
"self": 0.05304578999994192
},
"TrainerController.start_learning": {
"total": 605.8344515350002,
"count": 1,
"self": 0.6367364369789357,
"children": {
"TrainerController._reset_env": {
"total": 1.6643452430000707,
"count": 1,
"self": 1.6643452430000707
},
"TrainerController.advance": {
"total": 603.4427088910211,
"count": 18199,
"self": 0.2875258400463281,
"children": {
"env_step": {
"total": 603.1551830509748,
"count": 18199,
"self": 429.33385544599423,
"children": {
"SubprocessEnvManager._take_step": {
"total": 173.52477825698702,
"count": 18199,
"self": 1.4971410710024884,
"children": {
"TorchPolicy.evaluate": {
"total": 172.02763718598453,
"count": 18199,
"self": 172.02763718598453
}
}
},
"workers": {
"total": 0.29654934799350485,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 604.5951128360109,
"count": 18199,
"is_parallel": true,
"self": 385.3042974650091,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021467980000124953,
"count": 1,
"is_parallel": true,
"self": 0.0006779030002235231,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014688949997889722,
"count": 10,
"is_parallel": true,
"self": 0.0014688949997889722
}
}
},
"UnityEnvironment.step": {
"total": 0.034837900999946214,
"count": 1,
"is_parallel": true,
"self": 0.0006608210001104453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004448709998996492,
"count": 1,
"is_parallel": true,
"self": 0.0004448709998996492
},
"communicator.exchange": {
"total": 0.031876500999942436,
"count": 1,
"is_parallel": true,
"self": 0.031876500999942436
},
"steps_from_proto": {
"total": 0.0018557079999936832,
"count": 1,
"is_parallel": true,
"self": 0.0003528950001054909,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015028129998881923,
"count": 10,
"is_parallel": true,
"self": 0.0015028129998881923
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.29081537100183,
"count": 18198,
"is_parallel": true,
"self": 10.241952031000665,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.261837061990946,
"count": 18198,
"is_parallel": true,
"self": 5.261837061990946
},
"communicator.exchange": {
"total": 171.07970117699938,
"count": 18198,
"is_parallel": true,
"self": 171.07970117699938
},
"steps_from_proto": {
"total": 32.70732510101084,
"count": 18198,
"is_parallel": true,
"self": 6.309745509074219,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.39757959193662,
"count": 181980,
"is_parallel": true,
"self": 26.39757959193662
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012378200017337804,
"count": 1,
"self": 0.00012378200017337804,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 597.7480557482022,
"count": 707034,
"is_parallel": true,
"self": 14.714106445086145,
"children": {
"process_trajectory": {
"total": 244.9419569211159,
"count": 707034,
"is_parallel": true,
"self": 243.98783303911569,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9541238820002036,
"count": 4,
"is_parallel": true,
"self": 0.9541238820002036
}
}
},
"_update_policy": {
"total": 338.09199238200017,
"count": 90,
"is_parallel": true,
"self": 136.18059997000591,
"children": {
"TorchPPOOptimizer.update": {
"total": 201.91139241199426,
"count": 12224,
"is_parallel": true,
"self": 201.91139241199426
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09053718199993455,
"count": 1,
"self": 0.0009107429996220162,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08962643900031253,
"count": 1,
"self": 0.08962643900031253
}
}
}
}
}
}
}