ezrab's picture
First Push
44d4e9f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9783227443695068,
"min": 0.9783227443695068,
"max": 2.8260059356689453,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9297.9794921875,
"min": 9297.9794921875,
"max": 28847.869140625,
"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": 13.435583114624023,
"min": 0.3791485130786896,
"max": 13.435583114624023,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2619.938720703125,
"min": 73.5548095703125,
"max": 2720.817626953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06834098914580809,
"min": 0.06237608711785915,
"max": 0.0741352746611251,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27336395658323237,
"min": 0.2495043484714366,
"max": 0.36197200111257866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16250054140155223,
"min": 0.11008116554048862,
"max": 0.4441590140044105,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6500021656062089,
"min": 0.4403246621619545,
"max": 1.776636056017642,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.727272727272727,
"min": 3.3181818181818183,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1176.0,
"min": 146.0,
"max": 1457.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.727272727272727,
"min": 3.3181818181818183,
"max": 26.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1176.0,
"min": 146.0,
"max": 1457.0,
"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": "1741121718",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget3 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741122217"
},
"total": 498.94364424900004,
"count": 1,
"self": 0.44477960400035954,
"children": {
"run_training.setup": {
"total": 0.020415153999692848,
"count": 1,
"self": 0.020415153999692848
},
"TrainerController.start_learning": {
"total": 498.478449491,
"count": 1,
"self": 0.34929301898910126,
"children": {
"TrainerController._reset_env": {
"total": 2.0170371269996394,
"count": 1,
"self": 2.0170371269996394
},
"TrainerController.advance": {
"total": 489.8889427520112,
"count": 18192,
"self": 0.35883144902481945,
"children": {
"env_step": {
"total": 320.34574875299313,
"count": 18192,
"self": 233.1824791590534,
"children": {
"SubprocessEnvManager._take_step": {
"total": 86.95441248600127,
"count": 18192,
"self": 1.2958679149814998,
"children": {
"TorchPolicy.evaluate": {
"total": 85.65854457101977,
"count": 18192,
"self": 85.65854457101977
}
}
},
"workers": {
"total": 0.20885710793845647,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 490.19524170001205,
"count": 18192,
"is_parallel": true,
"self": 285.7295679270096,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021648080000886694,
"count": 1,
"is_parallel": true,
"self": 0.000713423000433977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014513849996546924,
"count": 10,
"is_parallel": true,
"self": 0.0014513849996546924
}
}
},
"UnityEnvironment.step": {
"total": 0.037061293000078877,
"count": 1,
"is_parallel": true,
"self": 0.0005682260007233708,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037712899984398973,
"count": 1,
"is_parallel": true,
"self": 0.00037712899984398973
},
"communicator.exchange": {
"total": 0.03429995199985569,
"count": 1,
"is_parallel": true,
"self": 0.03429995199985569
},
"steps_from_proto": {
"total": 0.0018159859996558225,
"count": 1,
"is_parallel": true,
"self": 0.0003701589994307142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014458270002251083,
"count": 10,
"is_parallel": true,
"self": 0.0014458270002251083
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.46567377300244,
"count": 18191,
"is_parallel": true,
"self": 9.69536283798061,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.537570243983282,
"count": 18191,
"is_parallel": true,
"self": 5.537570243983282
},
"communicator.exchange": {
"total": 156.8358005260111,
"count": 18191,
"is_parallel": true,
"self": 156.8358005260111
},
"steps_from_proto": {
"total": 32.396940165027445,
"count": 18191,
"is_parallel": true,
"self": 5.804696409132703,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.592243755894742,
"count": 181910,
"is_parallel": true,
"self": 26.592243755894742
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 169.18436254999324,
"count": 18192,
"self": 0.43275667298712506,
"children": {
"process_trajectory": {
"total": 52.919104031006555,
"count": 18192,
"self": 50.0160583460065,
"children": {
"RLTrainer._checkpoint": {
"total": 2.903045685000052,
"count": 4,
"self": 2.903045685000052
}
}
},
"_update_policy": {
"total": 115.83250184599956,
"count": 90,
"self": 38.66795394298106,
"children": {
"TorchPPOOptimizer.update": {
"total": 77.1645479030185,
"count": 4587,
"self": 77.1645479030185
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.470001375826541e-07,
"count": 1,
"self": 8.470001375826541e-07
},
"TrainerController._save_models": {
"total": 6.223175745999924,
"count": 1,
"self": 2.120330125000237,
"children": {
"RLTrainer._checkpoint": {
"total": 4.1028456209996875,
"count": 1,
"self": 4.1028456209996875
}
}
}
}
}
}
}