maavaneck's picture
First Push
1c9fcf4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9455358982086182,
"min": 0.9319064617156982,
"max": 2.8563950061798096,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9100.783203125,
"min": 9100.783203125,
"max": 29283.76171875,
"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": 12.860599517822266,
"min": 0.48874208331108093,
"max": 12.860599517822266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.81689453125,
"min": 94.81596374511719,
"max": 2611.240234375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07006254967977749,
"min": 0.06513879927769463,
"max": 0.07754806553195664,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28025019871910994,
"min": 0.27563344864614137,
"max": 0.3540333941425927,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19281496772286938,
"min": 0.15982787243396446,
"max": 0.302519000862159,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7712598708914775,
"min": 0.6393114897358578,
"max": 1.512595004310795,
"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.CumulativeReward.mean": {
"value": 25.522727272727273,
"min": 4.2272727272727275,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1123.0,
"min": 186.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.522727272727273,
"min": 4.2272727272727275,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1123.0,
"min": 186.0,
"max": 1390.0,
"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": "1724837788",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724838458"
},
"total": 670.104783744,
"count": 1,
"self": 0.9380577560000347,
"children": {
"run_training.setup": {
"total": 0.10633942499998739,
"count": 1,
"self": 0.10633942499998739
},
"TrainerController.start_learning": {
"total": 669.060386563,
"count": 1,
"self": 1.053743096005178,
"children": {
"TrainerController._reset_env": {
"total": 3.330989962999979,
"count": 1,
"self": 3.330989962999979
},
"TrainerController.advance": {
"total": 664.5360907619946,
"count": 18211,
"self": 0.4911217650009121,
"children": {
"env_step": {
"total": 664.0449689969937,
"count": 18211,
"self": 507.5255924659878,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.04337849600483,
"count": 18211,
"self": 2.9892408160063155,
"children": {
"TorchPolicy.evaluate": {
"total": 153.05413767999852,
"count": 18211,
"self": 153.05413767999852
}
}
},
"workers": {
"total": 0.4759980350010551,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 666.7742327700106,
"count": 18211,
"is_parallel": true,
"self": 310.28318032699957,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003976567000052,
"count": 1,
"is_parallel": true,
"self": 0.0010220630001072095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002954503999944791,
"count": 10,
"is_parallel": true,
"self": 0.002954503999944791
}
}
},
"UnityEnvironment.step": {
"total": 0.044723356000019976,
"count": 1,
"is_parallel": true,
"self": 0.0008807019999608201,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003962970000088717,
"count": 1,
"is_parallel": true,
"self": 0.0003962970000088717
},
"communicator.exchange": {
"total": 0.04105975300001319,
"count": 1,
"is_parallel": true,
"self": 0.04105975300001319
},
"steps_from_proto": {
"total": 0.002386604000037096,
"count": 1,
"is_parallel": true,
"self": 0.00045781500006114584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00192878899997595,
"count": 10,
"is_parallel": true,
"self": 0.00192878899997595
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 356.49105244301103,
"count": 18210,
"is_parallel": true,
"self": 16.80973042699867,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.286066796002501,
"count": 18210,
"is_parallel": true,
"self": 8.286066796002501
},
"communicator.exchange": {
"total": 282.0926835220026,
"count": 18210,
"is_parallel": true,
"self": 282.0926835220026
},
"steps_from_proto": {
"total": 49.302571698007284,
"count": 18210,
"is_parallel": true,
"self": 9.962241344988968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.34033035301832,
"count": 182100,
"is_parallel": true,
"self": 39.34033035301832
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00028461500005505513,
"count": 1,
"self": 0.00028461500005505513,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 656.9370077559438,
"count": 823411,
"is_parallel": true,
"self": 19.87670936698305,
"children": {
"process_trajectory": {
"total": 370.3461792139605,
"count": 823411,
"is_parallel": true,
"self": 368.9045872779603,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4415919360002363,
"count": 4,
"is_parallel": true,
"self": 1.4415919360002363
}
}
},
"_update_policy": {
"total": 266.7141191750003,
"count": 90,
"is_parallel": true,
"self": 62.16855524799712,
"children": {
"TorchPPOOptimizer.update": {
"total": 204.54556392700317,
"count": 4587,
"is_parallel": true,
"self": 204.54556392700317
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1392781270001251,
"count": 1,
"self": 0.002186256000186404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1370918709999387,
"count": 1,
"self": 0.1370918709999387
}
}
}
}
}
}
}