rdesarz's picture
First try
1e258e0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9873919486999512,
"min": 0.9873919486999512,
"max": 2.869516611099243,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9427.6181640625,
"min": 9427.6181640625,
"max": 29418.28515625,
"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": 12.909075736999512,
"min": 0.42252206802368164,
"max": 12.909075736999512,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.269775390625,
"min": 81.96928405761719,
"max": 2612.849609375,
"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": 0.06599690400574165,
"min": 0.06215408004337566,
"max": 0.07286466069145166,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2639876160229666,
"min": 0.2560380892987893,
"max": 0.3643233034572583,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19059575560922717,
"min": 0.11976080871068452,
"max": 0.28695734517247073,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7623830224369087,
"min": 0.4790432348427381,
"max": 1.3324102180845598,
"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": 25.295454545454547,
"min": 3.340909090909091,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 147.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.340909090909091,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 147.0,
"max": 1396.0,
"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": "1677257041",
"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": "1.22.4",
"end_time_seconds": "1677257414"
},
"total": 373.328709184,
"count": 1,
"self": 0.3767879090000861,
"children": {
"run_training.setup": {
"total": 0.10784292699986509,
"count": 1,
"self": 0.10784292699986509
},
"TrainerController.start_learning": {
"total": 372.84407834800004,
"count": 1,
"self": 0.4558316190059486,
"children": {
"TrainerController._reset_env": {
"total": 6.042739901999994,
"count": 1,
"self": 6.042739901999994
},
"TrainerController.advance": {
"total": 366.21222690499417,
"count": 18203,
"self": 0.2380176619658414,
"children": {
"env_step": {
"total": 365.9742092430283,
"count": 18203,
"self": 244.14029271701656,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.60805706399469,
"count": 18203,
"self": 1.2785871029977898,
"children": {
"TorchPolicy.evaluate": {
"total": 120.3294699609969,
"count": 18203,
"self": 24.03406705101179,
"children": {
"TorchPolicy.sample_actions": {
"total": 96.29540290998511,
"count": 18203,
"self": 96.29540290998511
}
}
}
}
},
"workers": {
"total": 0.22585946201706975,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 372.0764561689962,
"count": 18203,
"is_parallel": true,
"self": 191.99686977099168,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005150839999942036,
"count": 1,
"is_parallel": true,
"self": 0.003674984999861408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001475855000080628,
"count": 10,
"is_parallel": true,
"self": 0.001475855000080628
}
}
},
"UnityEnvironment.step": {
"total": 0.03593770900010895,
"count": 1,
"is_parallel": true,
"self": 0.0006352249999963533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000349850000020524,
"count": 1,
"is_parallel": true,
"self": 0.000349850000020524
},
"communicator.exchange": {
"total": 0.0324633029999859,
"count": 1,
"is_parallel": true,
"self": 0.0324633029999859
},
"steps_from_proto": {
"total": 0.0024893310001061764,
"count": 1,
"is_parallel": true,
"self": 0.0006181930000366265,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018711380000695499,
"count": 10,
"is_parallel": true,
"self": 0.0018711380000695499
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 180.0795863980045,
"count": 18202,
"is_parallel": true,
"self": 8.266786663049743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.595805211987454,
"count": 18202,
"is_parallel": true,
"self": 4.595805211987454
},
"communicator.exchange": {
"total": 140.63075115398806,
"count": 18202,
"is_parallel": true,
"self": 140.63075115398806
},
"steps_from_proto": {
"total": 26.58624336897924,
"count": 18202,
"is_parallel": true,
"self": 5.636745596953006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.949497772026234,
"count": 182020,
"is_parallel": true,
"self": 20.949497772026234
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016361199982384278,
"count": 1,
"self": 0.00016361199982384278,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 364.72059147400364,
"count": 244513,
"is_parallel": true,
"self": 5.050160086934056,
"children": {
"process_trajectory": {
"total": 204.28675346606997,
"count": 244513,
"is_parallel": true,
"self": 203.44488707807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8418663879999713,
"count": 4,
"is_parallel": true,
"self": 0.8418663879999713
}
}
},
"_update_policy": {
"total": 155.38367792099962,
"count": 90,
"is_parallel": true,
"self": 38.654181964999225,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.72949595600039,
"count": 4587,
"is_parallel": true,
"self": 116.72949595600039
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13311631000010493,
"count": 1,
"self": 0.0008453059999737889,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13227100400013114,
"count": 1,
"self": 0.13227100400013114
}
}
}
}
}
}
}