andli28's picture
First Push
7f069bc
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7183641195297241,
"min": 0.6727043986320496,
"max": 2.871943950653076,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6937.9609375,
"min": 6481.03662109375,
"max": 29474.759765625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.929606437683105,
"min": 0.30199524760246277,
"max": 13.929606437683105,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2855.5693359375,
"min": 58.58707809448242,
"max": 2855.5693359375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06003488234344723,
"min": 0.06003488234344723,
"max": 0.07371053359421043,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30017441171723613,
"min": 0.24721178848652497,
"max": 0.36855266797105213,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17260720539911117,
"min": 0.09220437206985319,
"max": 0.27729452480288114,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8630360269955559,
"min": 0.36881748827941274,
"max": 1.3864726240144056,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.272727272727273,
"min": 2.6136363636363638,
"max": 27.272727272727273,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1500.0,
"min": 115.0,
"max": 1500.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.272727272727273,
"min": 2.6136363636363638,
"max": 27.272727272727273,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1500.0,
"min": 115.0,
"max": 1500.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680811764",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680812952"
},
"total": 1188.0508080949999,
"count": 1,
"self": 0.48831623299997773,
"children": {
"run_training.setup": {
"total": 0.11395300499998484,
"count": 1,
"self": 0.11395300499998484
},
"TrainerController.start_learning": {
"total": 1187.448538857,
"count": 1,
"self": 1.3627281230301378,
"children": {
"TrainerController._reset_env": {
"total": 3.9441492219999645,
"count": 1,
"self": 3.9441492219999645
},
"TrainerController.advance": {
"total": 1182.0088643969696,
"count": 45476,
"self": 0.6993514629812125,
"children": {
"env_step": {
"total": 1181.3095129339883,
"count": 45476,
"self": 865.222462365977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.381528099015,
"count": 45476,
"self": 4.395896122018371,
"children": {
"TorchPolicy.evaluate": {
"total": 310.9856319769966,
"count": 45476,
"self": 310.9856319769966
}
}
},
"workers": {
"total": 0.7055224689963779,
"count": 45476,
"self": 0.0,
"children": {
"worker_root": {
"total": 1183.7526871979733,
"count": 45476,
"is_parallel": true,
"self": 543.8545109029926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0059111030000167375,
"count": 1,
"is_parallel": true,
"self": 0.004298982999898726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016121200001180114,
"count": 10,
"is_parallel": true,
"self": 0.0016121200001180114
}
}
},
"UnityEnvironment.step": {
"total": 0.04224272600004042,
"count": 1,
"is_parallel": true,
"self": 0.0005588770001168086,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035194499992030615,
"count": 1,
"is_parallel": true,
"self": 0.00035194499992030615
},
"communicator.exchange": {
"total": 0.039093839999964075,
"count": 1,
"is_parallel": true,
"self": 0.039093839999964075
},
"steps_from_proto": {
"total": 0.0022380640000392305,
"count": 1,
"is_parallel": true,
"self": 0.0004855470000393325,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001752516999999898,
"count": 10,
"is_parallel": true,
"self": 0.001752516999999898
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 639.8981762949807,
"count": 45475,
"is_parallel": true,
"self": 25.529835429954346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.612481194987481,
"count": 45475,
"is_parallel": true,
"self": 14.612481194987481
},
"communicator.exchange": {
"total": 514.4932364970316,
"count": 45475,
"is_parallel": true,
"self": 514.4932364970316
},
"steps_from_proto": {
"total": 85.26262317300723,
"count": 45475,
"is_parallel": true,
"self": 16.983541228964782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.27908194404245,
"count": 454750,
"is_parallel": true,
"self": 68.27908194404245
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.1911000127802254e-05,
"count": 1,
"self": 5.1911000127802254e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1172.887055800994,
"count": 1042086,
"is_parallel": true,
"self": 26.076359370080354,
"children": {
"process_trajectory": {
"total": 642.9990955379149,
"count": 1042086,
"is_parallel": true,
"self": 639.7822986679151,
"children": {
"RLTrainer._checkpoint": {
"total": 3.216796869999712,
"count": 10,
"is_parallel": true,
"self": 3.216796869999712
}
}
},
"_update_policy": {
"total": 503.81160089299874,
"count": 227,
"is_parallel": true,
"self": 187.19993816801218,
"children": {
"TorchPPOOptimizer.update": {
"total": 316.61166272498656,
"count": 11574,
"is_parallel": true,
"self": 316.61166272498656
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13274520400000256,
"count": 1,
"self": 0.0008924510000269947,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13185275299997556,
"count": 1,
"self": 0.13185275299997556
}
}
}
}
}
}
}