Haru4me's picture
First Push
cccaa6c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0176420211791992,
"min": 1.0176420211791992,
"max": 2.854051351547241,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9705.251953125,
"min": 9705.251953125,
"max": 29228.33984375,
"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": 25.504047393798828,
"min": 0.34141746163368225,
"max": 25.504047393798828,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4973.2890625,
"min": 66.2349853515625,
"max": 5166.4375,
"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": 0.07224892936310247,
"min": 0.05787431827333171,
"max": 0.07417584101009804,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2889957174524099,
"min": 0.23149727309332685,
"max": 0.3708792050504902,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20302760443997148,
"min": 0.13142647320979878,
"max": 0.36454202212831555,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8121104177598859,
"min": 0.5257058928391951,
"max": 1.7756521485599817,
"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": 25.568181818181817,
"min": 3.5454545454545454,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 156.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.5454545454545454,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 156.0,
"max": 1412.0,
"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": "1717149129",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717149575"
},
"total": 446.26194620499996,
"count": 1,
"self": 0.4352227459999085,
"children": {
"run_training.setup": {
"total": 0.05685297400003719,
"count": 1,
"self": 0.05685297400003719
},
"TrainerController.start_learning": {
"total": 445.769870485,
"count": 1,
"self": 0.5729425809939244,
"children": {
"TrainerController._reset_env": {
"total": 3.6522995909999736,
"count": 1,
"self": 3.6522995909999736
},
"TrainerController.advance": {
"total": 441.42402309700617,
"count": 18201,
"self": 0.2754153270076358,
"children": {
"env_step": {
"total": 441.14860776999853,
"count": 18201,
"self": 285.5810246890006,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.28303987400506,
"count": 18201,
"self": 1.4545835660050557,
"children": {
"TorchPolicy.evaluate": {
"total": 153.828456308,
"count": 18201,
"self": 153.828456308
}
}
},
"workers": {
"total": 0.28454320699285063,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.6052882730009,
"count": 18201,
"is_parallel": true,
"self": 228.5271968839989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00559120799999846,
"count": 1,
"is_parallel": true,
"self": 0.00397562799997786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016155800000206,
"count": 10,
"is_parallel": true,
"self": 0.0016155800000206
}
}
},
"UnityEnvironment.step": {
"total": 0.07616463800002293,
"count": 1,
"is_parallel": true,
"self": 0.0006765660000382923,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004010499999935746,
"count": 1,
"is_parallel": true,
"self": 0.0004010499999935746
},
"communicator.exchange": {
"total": 0.06946475299997701,
"count": 1,
"is_parallel": true,
"self": 0.06946475299997701
},
"steps_from_proto": {
"total": 0.005622269000014057,
"count": 1,
"is_parallel": true,
"self": 0.0004134470000849433,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005208821999929114,
"count": 10,
"is_parallel": true,
"self": 0.005208821999929114
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.078091389002,
"count": 18200,
"is_parallel": true,
"self": 9.98979463302237,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.223939954995103,
"count": 18200,
"is_parallel": true,
"self": 5.223939954995103
},
"communicator.exchange": {
"total": 168.66111196999316,
"count": 18200,
"is_parallel": true,
"self": 168.66111196999316
},
"steps_from_proto": {
"total": 32.203244830991366,
"count": 18200,
"is_parallel": true,
"self": 5.922938777989884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.280306053001482,
"count": 182000,
"is_parallel": true,
"self": 26.280306053001482
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014604599994072487,
"count": 1,
"self": 0.00014604599994072487,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 436.21935150997945,
"count": 664314,
"is_parallel": true,
"self": 13.388873130961997,
"children": {
"process_trajectory": {
"total": 240.42850022801764,
"count": 664314,
"is_parallel": true,
"self": 239.64119076101753,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7873094670001137,
"count": 4,
"is_parallel": true,
"self": 0.7873094670001137
}
}
},
"_update_policy": {
"total": 182.4019781509998,
"count": 90,
"is_parallel": true,
"self": 56.3019982860024,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.09997986499741,
"count": 4587,
"is_parallel": true,
"self": 126.09997986499741
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12045917000000372,
"count": 1,
"self": 0.0011382280000589162,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11932094199994481,
"count": 1,
"self": 0.11932094199994481
}
}
}
}
}
}
}