mustafataha5's picture
First Push from Colab
af47d3b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0146596431732178,
"min": 1.0146596431732178,
"max": 2.833373785018921,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9699.1318359375,
"min": 9699.1318359375,
"max": 29047.748046875,
"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": 11.92392349243164,
"min": 0.49157729744911194,
"max": 11.92392349243164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2325.1650390625,
"min": 95.36599731445312,
"max": 2393.48095703125,
"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": 0.06837877643285502,
"min": 0.059189168195806295,
"max": 0.07371869052522906,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27351510573142007,
"min": 0.2584841117678283,
"max": 0.3685934526261453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19829996762906804,
"min": 0.14510899383172976,
"max": 0.2570915146931714,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7931998705162722,
"min": 0.580435975326919,
"max": 1.2626727340268153,
"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": 24.113636363636363,
"min": 3.909090909090909,
"max": 24.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1061.0,
"min": 172.0,
"max": 1304.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.113636363636363,
"min": 3.909090909090909,
"max": 24.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1061.0,
"min": 172.0,
"max": 1304.0,
"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": "1754559539",
"python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.30.0",
"mlagents_envs_version": "0.30.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1754559965"
},
"total": 425.86801210500016,
"count": 1,
"self": 0.4312383360002059,
"children": {
"run_training.setup": {
"total": 0.018142795999665395,
"count": 1,
"self": 0.018142795999665395
},
"TrainerController.start_learning": {
"total": 425.4186309730003,
"count": 1,
"self": 0.5471208821072651,
"children": {
"TrainerController._reset_env": {
"total": 4.352526869999565,
"count": 1,
"self": 4.352526869999565
},
"TrainerController.advance": {
"total": 420.3808128878927,
"count": 18202,
"self": 0.25007299389289983,
"children": {
"env_step": {
"total": 420.1307398939998,
"count": 18202,
"self": 291.7574178740351,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.10922031593873,
"count": 18202,
"self": 1.6601711419352796,
"children": {
"TorchPolicy.evaluate": {
"total": 126.44904917400345,
"count": 18202,
"self": 126.44904917400345
}
}
},
"workers": {
"total": 0.2641017040259612,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.1518969379622,
"count": 18202,
"is_parallel": true,
"self": 202.09263224391816,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019646009995994973,
"count": 1,
"is_parallel": true,
"self": 0.0006335829984891461,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013310180011103512,
"count": 10,
"is_parallel": true,
"self": 0.0013310180011103512
}
}
},
"UnityEnvironment.step": {
"total": 0.04117205300008209,
"count": 1,
"is_parallel": true,
"self": 0.0005857969999851775,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038989899985608645,
"count": 1,
"is_parallel": true,
"self": 0.00038989899985608645
},
"communicator.exchange": {
"total": 0.0379791049999767,
"count": 1,
"is_parallel": true,
"self": 0.0379791049999767
},
"steps_from_proto": {
"total": 0.002217252000264125,
"count": 1,
"is_parallel": true,
"self": 0.00039540000125271035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018218519990114146,
"count": 10,
"is_parallel": true,
"self": 0.0018218519990114146
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 222.05926469404403,
"count": 18201,
"is_parallel": true,
"self": 9.594683527961024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.167762535925249,
"count": 18201,
"is_parallel": true,
"self": 5.167762535925249
},
"communicator.exchange": {
"total": 173.37468155709303,
"count": 18201,
"is_parallel": true,
"self": 173.37468155709303
},
"steps_from_proto": {
"total": 33.92213707306473,
"count": 18201,
"is_parallel": true,
"self": 6.3081395522285675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.613997520836165,
"count": 182010,
"is_parallel": true,
"self": 27.613997520836165
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001354890000584419,
"count": 1,
"self": 0.0001354890000584419,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 415.4053783142799,
"count": 649021,
"is_parallel": true,
"self": 13.264412587915103,
"children": {
"process_trajectory": {
"total": 221.54403715736862,
"count": 649021,
"is_parallel": true,
"self": 220.77419815636858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7698390010000367,
"count": 4,
"is_parallel": true,
"self": 0.7698390010000367
}
}
},
"_update_policy": {
"total": 180.5969285689962,
"count": 90,
"is_parallel": true,
"self": 62.55839686701438,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.03853170198181,
"count": 4587,
"is_parallel": true,
"self": 118.03853170198181
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13803484400068555,
"count": 1,
"self": 0.0008573560007789638,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1371774879999066,
"count": 1,
"self": 0.1371774879999066
}
}
}
}
}
}
}