michalcisek5's picture
push first model
f944b99
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9000555872917175,
"min": 0.9000555872917175,
"max": 2.863550901412964,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8593.73046875,
"min": 8593.73046875,
"max": 29325.625,
"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": 12.672791481018066,
"min": 0.355785608291626,
"max": 12.672791481018066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.1943359375,
"min": 69.02240753173828,
"max": 2541.803466796875,
"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": 0.06717995869357586,
"min": 0.06308145460492347,
"max": 0.07779322519983158,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26871983477430345,
"min": 0.2535595804465451,
"max": 0.3653899459590606,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1925727969729433,
"min": 0.13029456715779744,
"max": 0.27912972838270894,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7702911878917732,
"min": 0.5211782686311898,
"max": 1.328250044116787,
"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": 25.0,
"min": 3.590909090909091,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 158.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.590909090909091,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 158.0,
"max": 1391.0,
"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": "1678748384",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.20.0",
"end_time_seconds": "1678748861"
},
"total": 477.355782676,
"count": 1,
"self": 0.43522796800004926,
"children": {
"run_training.setup": {
"total": 0.050377180999930715,
"count": 1,
"self": 0.050377180999930715
},
"TrainerController.start_learning": {
"total": 476.870177527,
"count": 1,
"self": 0.553800131007165,
"children": {
"TrainerController._reset_env": {
"total": 5.224930388999951,
"count": 1,
"self": 5.224930388999951
},
"TrainerController.advance": {
"total": 470.97317274299303,
"count": 18201,
"self": 0.26410934497835115,
"children": {
"env_step": {
"total": 470.7090633980147,
"count": 18201,
"self": 337.45867275601756,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.97714278199965,
"count": 18201,
"self": 1.5831224540094126,
"children": {
"TorchPolicy.evaluate": {
"total": 131.39402032799023,
"count": 18201,
"self": 29.230359955986614,
"children": {
"TorchPolicy.sample_actions": {
"total": 102.16366037200362,
"count": 18201,
"self": 102.16366037200362
}
}
}
}
},
"workers": {
"total": 0.27324785999746837,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 474.76417642399247,
"count": 18201,
"is_parallel": true,
"self": 226.58243789398614,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021436320000702835,
"count": 1,
"is_parallel": true,
"self": 0.0007471220001207257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013965099999495578,
"count": 10,
"is_parallel": true,
"self": 0.0013965099999495578
}
}
},
"UnityEnvironment.step": {
"total": 0.07891245899998012,
"count": 1,
"is_parallel": true,
"self": 0.000606071999982305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044264199993904185,
"count": 1,
"is_parallel": true,
"self": 0.00044264199993904185
},
"communicator.exchange": {
"total": 0.07184274000007917,
"count": 1,
"is_parallel": true,
"self": 0.07184274000007917
},
"steps_from_proto": {
"total": 0.006021004999979596,
"count": 1,
"is_parallel": true,
"self": 0.004152197000053093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018688079999265028,
"count": 10,
"is_parallel": true,
"self": 0.0018688079999265028
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 248.18173853000633,
"count": 18200,
"is_parallel": true,
"self": 9.946238773027858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.368968443015206,
"count": 18200,
"is_parallel": true,
"self": 5.368968443015206
},
"communicator.exchange": {
"total": 200.00547357098446,
"count": 18200,
"is_parallel": true,
"self": 200.00547357098446
},
"steps_from_proto": {
"total": 32.8610577429788,
"count": 18200,
"is_parallel": true,
"self": 7.4314052779750455,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.429652465003755,
"count": 182000,
"is_parallel": true,
"self": 25.429652465003755
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011492299995552457,
"count": 1,
"self": 0.00011492299995552457,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 467.3105158609219,
"count": 440408,
"is_parallel": true,
"self": 10.698375322923425,
"children": {
"process_trajectory": {
"total": 264.00460192699893,
"count": 440408,
"is_parallel": true,
"self": 262.921432790999,
"children": {
"RLTrainer._checkpoint": {
"total": 1.083169135999924,
"count": 4,
"is_parallel": true,
"self": 1.083169135999924
}
}
},
"_update_policy": {
"total": 192.60753861099954,
"count": 90,
"is_parallel": true,
"self": 82.33258389199386,
"children": {
"TorchPPOOptimizer.update": {
"total": 110.27495471900568,
"count": 4584,
"is_parallel": true,
"self": 110.27495471900568
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11815934099990955,
"count": 1,
"self": 0.0008841970000048605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11727514399990469,
"count": 1,
"self": 0.11727514399990469
}
}
}
}
}
}
}