amal94's picture
First Push
6d011fe
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8902278542518616,
"min": 0.8902278542518616,
"max": 2.860339641571045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8539.0654296875,
"min": 8539.0654296875,
"max": 29292.73828125,
"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": 12.761195182800293,
"min": 0.4523272216320038,
"max": 12.761195182800293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2488.43310546875,
"min": 87.75148010253906,
"max": 2602.30078125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0686060997288544,
"min": 0.06287711983952927,
"max": 0.07359149805983464,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2744243989154176,
"min": 0.2515084793581171,
"max": 0.36795749029917324,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17806608346747418,
"min": 0.13278004065082938,
"max": 0.3054208324528208,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7122643338698967,
"min": 0.5311201626033175,
"max": 1.456682475466354,
"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": 3.477272727272727,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.113636363636363,
"min": 3.477272727272727,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1105.0,
"min": 153.0,
"max": 1376.0,
"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": "1684166372",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684166813"
},
"total": 441.6208479400001,
"count": 1,
"self": 0.4316402910000079,
"children": {
"run_training.setup": {
"total": 0.0632170410000299,
"count": 1,
"self": 0.0632170410000299
},
"TrainerController.start_learning": {
"total": 441.12599060800005,
"count": 1,
"self": 0.5018331719950311,
"children": {
"TrainerController._reset_env": {
"total": 4.021377846000064,
"count": 1,
"self": 4.021377846000064
},
"TrainerController.advance": {
"total": 436.46523508300515,
"count": 18205,
"self": 0.2435687780018725,
"children": {
"env_step": {
"total": 436.2216663050033,
"count": 18205,
"self": 318.2297690340117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 117.75116630399714,
"count": 18205,
"self": 1.6407673820000355,
"children": {
"TorchPolicy.evaluate": {
"total": 116.1103989219971,
"count": 18205,
"self": 116.1103989219971
}
}
},
"workers": {
"total": 0.24073096699441976,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 439.7842654049997,
"count": 18205,
"is_parallel": true,
"self": 207.1925508319947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052333630000021,
"count": 1,
"is_parallel": true,
"self": 0.0037839509997183995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014494120002837008,
"count": 10,
"is_parallel": true,
"self": 0.0014494120002837008
}
}
},
"UnityEnvironment.step": {
"total": 0.0474206179999328,
"count": 1,
"is_parallel": true,
"self": 0.0006111570000939537,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005279509999809306,
"count": 1,
"is_parallel": true,
"self": 0.0005279509999809306
},
"communicator.exchange": {
"total": 0.04420638699991741,
"count": 1,
"is_parallel": true,
"self": 0.04420638699991741
},
"steps_from_proto": {
"total": 0.002075122999940504,
"count": 1,
"is_parallel": true,
"self": 0.0004814609998220476,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015936620001184565,
"count": 10,
"is_parallel": true,
"self": 0.0015936620001184565
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.591714573005,
"count": 18204,
"is_parallel": true,
"self": 10.024458115007974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.011297340004035,
"count": 18204,
"is_parallel": true,
"self": 5.011297340004035
},
"communicator.exchange": {
"total": 184.771098059991,
"count": 18204,
"is_parallel": true,
"self": 184.771098059991
},
"steps_from_proto": {
"total": 32.78486105800198,
"count": 18204,
"is_parallel": true,
"self": 5.931573112025603,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.853287945976376,
"count": 182040,
"is_parallel": true,
"self": 26.853287945976376
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011722199997166172,
"count": 1,
"self": 0.00011722199997166172,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 433.22049435298504,
"count": 408670,
"is_parallel": true,
"self": 9.09767820798993,
"children": {
"process_trajectory": {
"total": 236.88749347799467,
"count": 408670,
"is_parallel": true,
"self": 235.7338087099946,
"children": {
"RLTrainer._checkpoint": {
"total": 1.153684768000062,
"count": 4,
"is_parallel": true,
"self": 1.153684768000062
}
}
},
"_update_policy": {
"total": 187.23532266700045,
"count": 90,
"is_parallel": true,
"self": 71.1770043980041,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.05831826899635,
"count": 4587,
"is_parallel": true,
"self": 116.05831826899635
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1374272849998306,
"count": 1,
"self": 0.0008780639998349216,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13654922099999567,
"count": 1,
"self": 0.13654922099999567
}
}
}
}
}
}
}