dragovoid's picture
First Push
2951136 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7816714644432068,
"min": 0.7816714644432068,
"max": 2.8615355491638184,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7429.005859375,
"min": 7429.005859375,
"max": 29210.5546875,
"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": 13.236884117126465,
"min": 0.3607938587665558,
"max": 13.236884117126465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2581.1923828125,
"min": 69.99401092529297,
"max": 2669.9296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06900443368138832,
"min": 0.06451811960562505,
"max": 0.07673600430893666,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2760177347255533,
"min": 0.2580724784225002,
"max": 0.3537737001235798,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18862413709946707,
"min": 0.12386238202338527,
"max": 0.3043088303769336,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7544965483978683,
"min": 0.4954495280935411,
"max": 1.4521041792981764,
"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": 26.136363636363637,
"min": 3.3863636363636362,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1150.0,
"min": 149.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.136363636363637,
"min": 3.3863636363636362,
"max": 26.136363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1150.0,
"min": 149.0,
"max": 1416.0,
"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": "1733593429",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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 --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733593849"
},
"total": 420.1871814909998,
"count": 1,
"self": 0.42424415999971643,
"children": {
"run_training.setup": {
"total": 0.05750904699993953,
"count": 1,
"self": 0.05750904699993953
},
"TrainerController.start_learning": {
"total": 419.70542828400016,
"count": 1,
"self": 0.3301945360165064,
"children": {
"TrainerController._reset_env": {
"total": 2.031836271999964,
"count": 1,
"self": 2.031836271999964
},
"TrainerController.advance": {
"total": 417.26092877698375,
"count": 18192,
"self": 0.3459884399878774,
"children": {
"env_step": {
"total": 293.64366299599806,
"count": 18192,
"self": 223.07395313396137,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.35495922801033,
"count": 18192,
"self": 1.2097015279907737,
"children": {
"TorchPolicy.evaluate": {
"total": 69.14525770001956,
"count": 18192,
"self": 69.14525770001956
}
}
},
"workers": {
"total": 0.21475063402635897,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 418.3965407019916,
"count": 18192,
"is_parallel": true,
"self": 223.2856512910023,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022451669999554724,
"count": 1,
"is_parallel": true,
"self": 0.0006849459998647944,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001560221000090678,
"count": 10,
"is_parallel": true,
"self": 0.001560221000090678
}
}
},
"UnityEnvironment.step": {
"total": 0.0348170569998274,
"count": 1,
"is_parallel": true,
"self": 0.0006377169997904275,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040625700012242305,
"count": 1,
"is_parallel": true,
"self": 0.00040625700012242305
},
"communicator.exchange": {
"total": 0.031895593999934135,
"count": 1,
"is_parallel": true,
"self": 0.031895593999934135
},
"steps_from_proto": {
"total": 0.0018774889999804145,
"count": 1,
"is_parallel": true,
"self": 0.0003607749997627252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015167140002176893,
"count": 10,
"is_parallel": true,
"self": 0.0015167140002176893
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.11088941098933,
"count": 18191,
"is_parallel": true,
"self": 9.857279552990349,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.460241335979845,
"count": 18191,
"is_parallel": true,
"self": 5.460241335979845
},
"communicator.exchange": {
"total": 148.46761476700885,
"count": 18191,
"is_parallel": true,
"self": 148.46761476700885
},
"steps_from_proto": {
"total": 31.325753755010282,
"count": 18191,
"is_parallel": true,
"self": 5.515205202998914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.81054855201137,
"count": 181910,
"is_parallel": true,
"self": 25.81054855201137
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.27127734099781,
"count": 18192,
"self": 0.3927246169944283,
"children": {
"process_trajectory": {
"total": 27.879573721003908,
"count": 18192,
"self": 27.442298533004077,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43727518799983045,
"count": 4,
"self": 0.43727518799983045
}
}
},
"_update_policy": {
"total": 94.99897900299948,
"count": 90,
"self": 38.940218921002725,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.05876008199675,
"count": 4587,
"self": 56.05876008199675
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.041999894368928e-06,
"count": 1,
"self": 1.041999894368928e-06
},
"TrainerController._save_models": {
"total": 0.08246765700005199,
"count": 1,
"self": 0.0013036320001447166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08116402499990727,
"count": 1,
"self": 0.08116402499990727
}
}
}
}
}
}
}