stevaras2's picture
First Push
dffe017
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0359985828399658,
"min": 1.0359985828399658,
"max": 2.8678743839263916,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9891.71484375,
"min": 9891.71484375,
"max": 29369.900390625,
"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": 12.703743934631348,
"min": 0.35600554943084717,
"max": 12.712552070617676,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2477.22998046875,
"min": 69.06507873535156,
"max": 2593.360595703125,
"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": 0.07269933213312613,
"min": 0.06165715046701699,
"max": 0.07648400278405604,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2907973285325045,
"min": 0.24662860186806795,
"max": 0.373355583610771,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19578154319349458,
"min": 0.131332331460298,
"max": 0.2906818576303183,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7831261727739783,
"min": 0.525329325841192,
"max": 1.4534092881515914,
"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": 25.113636363636363,
"min": 3.522727272727273,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 155.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.522727272727273,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 155.0,
"max": 1375.0,
"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": "1674737240",
"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": "1.21.6",
"end_time_seconds": "1674737683"
},
"total": 443.565574516,
"count": 1,
"self": 0.44755098100000623,
"children": {
"run_training.setup": {
"total": 0.10255419300000312,
"count": 1,
"self": 0.10255419300000312
},
"TrainerController.start_learning": {
"total": 443.015469342,
"count": 1,
"self": 0.49729987999586456,
"children": {
"TrainerController._reset_env": {
"total": 9.39372300399998,
"count": 1,
"self": 9.39372300399998
},
"TrainerController.advance": {
"total": 433.0045751240043,
"count": 18202,
"self": 0.2665763900042748,
"children": {
"env_step": {
"total": 432.73799873400003,
"count": 18202,
"self": 280.1284280689892,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.34836728300053,
"count": 18202,
"self": 1.4393107619983425,
"children": {
"TorchPolicy.evaluate": {
"total": 150.90905652100219,
"count": 18202,
"self": 34.263079823998225,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.64597669700396,
"count": 18202,
"self": 116.64597669700396
}
}
}
}
},
"workers": {
"total": 0.2612033820103079,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.8076703029996,
"count": 18202,
"is_parallel": true,
"self": 218.08139529399728,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005706110000005538,
"count": 1,
"is_parallel": true,
"self": 0.0031630609999524495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002543049000053088,
"count": 10,
"is_parallel": true,
"self": 0.002543049000053088
}
}
},
"UnityEnvironment.step": {
"total": 0.04059327800001711,
"count": 1,
"is_parallel": true,
"self": 0.0004719000000363849,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003561759999684,
"count": 1,
"is_parallel": true,
"self": 0.0003561759999684
},
"communicator.exchange": {
"total": 0.03816915800001652,
"count": 1,
"is_parallel": true,
"self": 0.03816915800001652
},
"steps_from_proto": {
"total": 0.0015960439999957998,
"count": 1,
"is_parallel": true,
"self": 0.0004130900001086957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011829539998871041,
"count": 10,
"is_parallel": true,
"self": 0.0011829539998871041
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.72627500900234,
"count": 18201,
"is_parallel": true,
"self": 8.25030964499939,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.425664926006618,
"count": 18201,
"is_parallel": true,
"self": 5.425664926006618
},
"communicator.exchange": {
"total": 179.59873199399823,
"count": 18201,
"is_parallel": true,
"self": 179.59873199399823
},
"steps_from_proto": {
"total": 30.4515684439981,
"count": 18201,
"is_parallel": true,
"self": 6.695072312982006,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.756496131016092,
"count": 182010,
"is_parallel": true,
"self": 23.756496131016092
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.318899993904779e-05,
"count": 1,
"self": 4.318899993904779e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 429.7290055610214,
"count": 357786,
"is_parallel": true,
"self": 9.62871796600308,
"children": {
"process_trajectory": {
"total": 246.164082815018,
"count": 357786,
"is_parallel": true,
"self": 245.32537908101796,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8387037340000347,
"count": 4,
"is_parallel": true,
"self": 0.8387037340000347
}
}
},
"_update_policy": {
"total": 173.9362047800003,
"count": 90,
"is_parallel": true,
"self": 44.03059095699797,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.90561382300234,
"count": 4587,
"is_parallel": true,
"self": 129.90561382300234
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11982814499992855,
"count": 1,
"self": 0.000831571999924563,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11899657300000399,
"count": 1,
"self": 0.11899657300000399
}
}
}
}
}
}
}