jiaqihe's picture
First Push
7c8ff46 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0166627168655396,
"min": 1.010054111480713,
"max": 2.8697702884674072,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9729.4619140625,
"min": 9729.4619140625,
"max": 29420.884765625,
"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": 12.605989456176758,
"min": 0.23285003006458282,
"max": 12.605989456176758,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2458.16796875,
"min": 45.17290496826172,
"max": 2566.21630859375,
"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": 0.07007677723852206,
"min": 0.059210764114774134,
"max": 0.07343684251639335,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2803071089540882,
"min": 0.23684305645909653,
"max": 0.3671842125819667,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20565297206242877,
"min": 0.10640262480249957,
"max": 0.28811931206899527,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8226118882497151,
"min": 0.42561049920999827,
"max": 1.4405965603449764,
"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": 24.5,
"min": 3.25,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1078.0,
"min": 143.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.5,
"min": 3.25,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1078.0,
"min": 143.0,
"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": "1729750390",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729750990"
},
"total": 599.982259502,
"count": 1,
"self": 0.533342456000014,
"children": {
"run_training.setup": {
"total": 0.10582521100002396,
"count": 1,
"self": 0.10582521100002396
},
"TrainerController.start_learning": {
"total": 599.343091835,
"count": 1,
"self": 0.8468611119999423,
"children": {
"TrainerController._reset_env": {
"total": 6.524084466999966,
"count": 1,
"self": 6.524084466999966
},
"TrainerController.advance": {
"total": 591.8851352450001,
"count": 18203,
"self": 0.42075432800345425,
"children": {
"env_step": {
"total": 591.4643809169967,
"count": 18203,
"self": 455.0327741639857,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.02636538800465,
"count": 18203,
"self": 2.2803714330036655,
"children": {
"TorchPolicy.evaluate": {
"total": 133.74599395500098,
"count": 18203,
"self": 133.74599395500098
}
}
},
"workers": {
"total": 0.4052413650063045,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 597.477349254999,
"count": 18203,
"is_parallel": true,
"self": 287.8901423299939,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007145349999973405,
"count": 1,
"is_parallel": true,
"self": 0.0035402809999141027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003605069000059302,
"count": 10,
"is_parallel": true,
"self": 0.003605069000059302
}
}
},
"UnityEnvironment.step": {
"total": 0.05089184599995633,
"count": 1,
"is_parallel": true,
"self": 0.0007722909999188232,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004744010000194976,
"count": 1,
"is_parallel": true,
"self": 0.0004744010000194976
},
"communicator.exchange": {
"total": 0.047286196000015934,
"count": 1,
"is_parallel": true,
"self": 0.047286196000015934
},
"steps_from_proto": {
"total": 0.002358958000002076,
"count": 1,
"is_parallel": true,
"self": 0.00047661799987963605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00188234000012244,
"count": 10,
"is_parallel": true,
"self": 0.00188234000012244
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 309.5872069250051,
"count": 18202,
"is_parallel": true,
"self": 14.923590425009593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.550504095998463,
"count": 18202,
"is_parallel": true,
"self": 7.550504095998463
},
"communicator.exchange": {
"total": 242.99364861499953,
"count": 18202,
"is_parallel": true,
"self": 242.99364861499953
},
"steps_from_proto": {
"total": 44.11946378899751,
"count": 18202,
"is_parallel": true,
"self": 8.827055888998927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.29240789999858,
"count": 182020,
"is_parallel": true,
"self": 35.29240789999858
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001382809999768142,
"count": 1,
"self": 0.0001382809999768142,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 584.8718503779546,
"count": 766957,
"is_parallel": true,
"self": 17.702161947002878,
"children": {
"process_trajectory": {
"total": 310.6105849709516,
"count": 766957,
"is_parallel": true,
"self": 309.8297977809516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7807871900000123,
"count": 4,
"is_parallel": true,
"self": 0.7807871900000123
}
}
},
"_update_policy": {
"total": 256.55910346000013,
"count": 90,
"is_parallel": true,
"self": 73.91853739499959,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.64056606500054,
"count": 4587,
"is_parallel": true,
"self": 182.64056606500054
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08687272999998186,
"count": 1,
"self": 0.0012292019999904369,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08564352799999142,
"count": 1,
"self": 0.08564352799999142
}
}
}
}
}
}
}