markanite's picture
First Push
c115616 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8885252475738525,
"min": 0.8791638016700745,
"max": 2.8688440322875977,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8473.865234375,
"min": 8473.865234375,
"max": 29348.2734375,
"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": 12.739365577697754,
"min": 0.34392988681793213,
"max": 12.739365577697754,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2484.17626953125,
"min": 66.72239685058594,
"max": 2594.7177734375,
"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": 0.07431715411760653,
"min": 0.06356797067456485,
"max": 0.07492564624682178,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29726861647042613,
"min": 0.26638686568955616,
"max": 0.37462823123410893,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2234649824745515,
"min": 0.08810877688822574,
"max": 0.29513811524592193,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.893859929898206,
"min": 0.35243510755290297,
"max": 1.3407882262094348,
"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": 25.045454545454547,
"min": 2.75,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 121.0,
"max": 1380.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 2.75,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 121.0,
"max": 1380.0,
"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": "1722202385",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722202866"
},
"total": 481.609065491,
"count": 1,
"self": 0.4356669129999773,
"children": {
"run_training.setup": {
"total": 0.06415599600006772,
"count": 1,
"self": 0.06415599600006772
},
"TrainerController.start_learning": {
"total": 481.109242582,
"count": 1,
"self": 0.7338445889969307,
"children": {
"TrainerController._reset_env": {
"total": 3.0568444429999317,
"count": 1,
"self": 3.0568444429999317
},
"TrainerController.advance": {
"total": 477.2246423440031,
"count": 18201,
"self": 0.33122948000107044,
"children": {
"env_step": {
"total": 476.893412864002,
"count": 18201,
"self": 311.22885837400725,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.31892286999118,
"count": 18201,
"self": 1.6796842700051684,
"children": {
"TorchPolicy.evaluate": {
"total": 163.63923859998602,
"count": 18201,
"self": 163.63923859998602
}
}
},
"workers": {
"total": 0.34563162000358716,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 479.6016350060095,
"count": 18201,
"is_parallel": true,
"self": 239.61671453801603,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00580711199995676,
"count": 1,
"is_parallel": true,
"self": 0.004109715999788932,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016973960001678279,
"count": 10,
"is_parallel": true,
"self": 0.0016973960001678279
}
}
},
"UnityEnvironment.step": {
"total": 0.08465844099998776,
"count": 1,
"is_parallel": true,
"self": 0.000770536999880278,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004172600000629245,
"count": 1,
"is_parallel": true,
"self": 0.0004172600000629245
},
"communicator.exchange": {
"total": 0.08164812900008656,
"count": 1,
"is_parallel": true,
"self": 0.08164812900008656
},
"steps_from_proto": {
"total": 0.0018225149999580026,
"count": 1,
"is_parallel": true,
"self": 0.0003647259999297603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014577890000282423,
"count": 10,
"is_parallel": true,
"self": 0.0014577890000282423
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.98492046799345,
"count": 18200,
"is_parallel": true,
"self": 11.044289952013742,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.693803742005343,
"count": 18200,
"is_parallel": true,
"self": 5.693803742005343
},
"communicator.exchange": {
"total": 188.3227644899863,
"count": 18200,
"is_parallel": true,
"self": 188.3227644899863
},
"steps_from_proto": {
"total": 34.924062283988064,
"count": 18200,
"is_parallel": true,
"self": 7.109330148957497,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.814732135030567,
"count": 182000,
"is_parallel": true,
"self": 27.814732135030567
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012412499995662074,
"count": 1,
"self": 0.00012412499995662074,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 471.48592784703783,
"count": 727486,
"is_parallel": true,
"self": 15.144662995113663,
"children": {
"process_trajectory": {
"total": 262.40226035092405,
"count": 727486,
"is_parallel": true,
"self": 261.70080382892434,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7014565219997166,
"count": 4,
"is_parallel": true,
"self": 0.7014565219997166
}
}
},
"_update_policy": {
"total": 193.9390045010001,
"count": 90,
"is_parallel": true,
"self": 58.30824491699241,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.6307595840077,
"count": 4587,
"is_parallel": true,
"self": 135.6307595840077
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09378708100007316,
"count": 1,
"self": 0.001012687000184087,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09277439399988907,
"count": 1,
"self": 0.09277439399988907
}
}
}
}
}
}
}