Nihash009's picture
First and last push
3119c85 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5816439390182495,
"min": 1.5816439390182495,
"max": 2.8380253314971924,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 16284.60546875,
"min": 15624.48046875,
"max": 28970.5625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.420485496520996,
"min": 0.3667643368244171,
"max": 8.420485496520996,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1717.779052734375,
"min": 71.15228271484375,
"max": 1717.779052734375,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07129941081374828,
"min": 0.05741292888198194,
"max": 0.07500271649690808,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.35649705406874144,
"min": 0.2654802142790811,
"max": 0.3750135824845404,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.25485363900661473,
"min": 0.11894235099031242,
"max": 0.2950659809889747,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.2742681950330736,
"min": 0.47576940396124967,
"max": 1.3713965264021182,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 17.854545454545455,
"min": 3.272727272727273,
"max": 17.854545454545455,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 982.0,
"min": 144.0,
"max": 982.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.854545454545455,
"min": 3.272727272727273,
"max": 17.854545454545455,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 982.0,
"min": 144.0,
"max": 982.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1778918027",
"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=SnowballTarget2 --no-graphics",
"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": "1778918320"
},
"total": 293.4292082520001,
"count": 1,
"self": 0.5306210130002,
"children": {
"run_training.setup": {
"total": 0.040990980999595195,
"count": 1,
"self": 0.040990980999595195
},
"TrainerController.start_learning": {
"total": 292.8575962580003,
"count": 1,
"self": 0.3113080109956172,
"children": {
"TrainerController._reset_env": {
"total": 2.4884118169998146,
"count": 1,
"self": 2.4884118169998146
},
"TrainerController.advance": {
"total": 289.9786158950046,
"count": 9128,
"self": 0.3544603270188418,
"children": {
"env_step": {
"total": 208.64827082598958,
"count": 9128,
"self": 181.36076291302015,
"children": {
"SubprocessEnvManager._take_step": {
"total": 27.10653055597959,
"count": 9128,
"self": 0.9916507449788696,
"children": {
"TorchPolicy.evaluate": {
"total": 26.11487981100072,
"count": 9128,
"self": 26.11487981100072
}
}
},
"workers": {
"total": 0.18097735698984252,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 291.26976329096897,
"count": 9128,
"is_parallel": true,
"self": 134.3443741459805,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003873388999636518,
"count": 1,
"is_parallel": true,
"self": 0.001287240000692691,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002586148998943827,
"count": 10,
"is_parallel": true,
"self": 0.002586148998943827
}
}
},
"UnityEnvironment.step": {
"total": 0.050096486000256846,
"count": 1,
"is_parallel": true,
"self": 0.000686307000250963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004530910000539734,
"count": 1,
"is_parallel": true,
"self": 0.0004530910000539734
},
"communicator.exchange": {
"total": 0.04663574599999265,
"count": 1,
"is_parallel": true,
"self": 0.04663574599999265
},
"steps_from_proto": {
"total": 0.002321341999959259,
"count": 1,
"is_parallel": true,
"self": 0.0004422520000844088,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00187908999987485,
"count": 10,
"is_parallel": true,
"self": 0.00187908999987485
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 156.92538914498846,
"count": 9127,
"is_parallel": true,
"self": 7.024151305943633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.9328888860191,
"count": 9127,
"is_parallel": true,
"self": 3.9328888860191
},
"communicator.exchange": {
"total": 121.93459761300437,
"count": 9127,
"is_parallel": true,
"self": 121.93459761300437
},
"steps_from_proto": {
"total": 24.033751340021354,
"count": 9127,
"is_parallel": true,
"self": 4.29223849910295,
"children": {
"_process_rank_one_or_two_observation": {
"total": 19.741512840918404,
"count": 91270,
"is_parallel": true,
"self": 19.741512840918404
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 80.9758847419962,
"count": 9128,
"self": 0.41542955497334333,
"children": {
"process_trajectory": {
"total": 15.555540602023939,
"count": 9128,
"self": 15.271828043024016,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2837125589999232,
"count": 2,
"self": 0.2837125589999232
}
}
},
"_update_policy": {
"total": 65.00491458499891,
"count": 45,
"self": 24.817337631979626,
"children": {
"TorchPPOOptimizer.update": {
"total": 40.18757695301929,
"count": 2292,
"self": 40.18757695301929
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3120002222422045e-06,
"count": 1,
"self": 1.3120002222422045e-06
},
"TrainerController._save_models": {
"total": 0.0792592230000082,
"count": 1,
"self": 0.001024935999794252,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07823428700021395,
"count": 1,
"self": 0.07823428700021395
}
}
}
}
}
}
}