bastienm's picture
First training of SnowballTarget
c77ed5c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9102216958999634,
"min": 0.9102216958999634,
"max": 2.86466646194458,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8720.833984375,
"min": 8720.833984375,
"max": 29337.048828125,
"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": 12.230796813964844,
"min": 0.47096163034439087,
"max": 12.230796813964844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2385.00537109375,
"min": 91.3665542602539,
"max": 2461.491943359375,
"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": 0.07044513717147649,
"min": 0.06212669539992359,
"max": 0.07788738676782825,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28178054868590596,
"min": 0.2495981691023974,
"max": 0.38943693383914124,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20375834467510381,
"min": 0.13996256313368896,
"max": 0.29555411724483266,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8150333787004153,
"min": 0.5598502525347558,
"max": 1.3961662392990262,
"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": 24.863636363636363,
"min": 3.727272727272727,
"max": 24.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1094.0,
"min": 164.0,
"max": 1322.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.863636363636363,
"min": 3.727272727272727,
"max": 24.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1094.0,
"min": 164.0,
"max": 1322.0,
"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": "1684170013",
"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": "1684170609"
},
"total": 595.938309756,
"count": 1,
"self": 0.5370008890001827,
"children": {
"run_training.setup": {
"total": 0.07994639199989706,
"count": 1,
"self": 0.07994639199989706
},
"TrainerController.start_learning": {
"total": 595.3213624749999,
"count": 1,
"self": 0.8449257100106706,
"children": {
"TrainerController._reset_env": {
"total": 1.432333031999974,
"count": 1,
"self": 1.432333031999974
},
"TrainerController.advance": {
"total": 592.8887772349892,
"count": 18205,
"self": 0.39662748999376163,
"children": {
"env_step": {
"total": 592.4921497449955,
"count": 18205,
"self": 482.67590764200054,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.4162719739918,
"count": 18205,
"self": 2.8547600259788624,
"children": {
"TorchPolicy.evaluate": {
"total": 106.56151194801294,
"count": 18205,
"self": 106.56151194801294
}
}
},
"workers": {
"total": 0.39997012900312257,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 593.0109830210054,
"count": 18205,
"is_parallel": true,
"self": 255.02750692800691,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010218323999993117,
"count": 1,
"is_parallel": true,
"self": 0.006818021999833945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003400302000159172,
"count": 10,
"is_parallel": true,
"self": 0.003400302000159172
}
}
},
"UnityEnvironment.step": {
"total": 0.1115424700000176,
"count": 1,
"is_parallel": true,
"self": 0.0007595340000534634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005593930000031833,
"count": 1,
"is_parallel": true,
"self": 0.0005593930000031833
},
"communicator.exchange": {
"total": 0.10111158899997008,
"count": 1,
"is_parallel": true,
"self": 0.10111158899997008
},
"steps_from_proto": {
"total": 0.009111953999990874,
"count": 1,
"is_parallel": true,
"self": 0.0005064229999334202,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008605531000057454,
"count": 10,
"is_parallel": true,
"self": 0.008605531000057454
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 337.98347609299844,
"count": 18204,
"is_parallel": true,
"self": 14.009437231002039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.672379686980321,
"count": 18204,
"is_parallel": true,
"self": 7.672379686980321
},
"communicator.exchange": {
"total": 269.81791683000097,
"count": 18204,
"is_parallel": true,
"self": 269.81791683000097
},
"steps_from_proto": {
"total": 46.483742345015116,
"count": 18204,
"is_parallel": true,
"self": 9.164379521021147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.31936282399397,
"count": 182040,
"is_parallel": true,
"self": 37.31936282399397
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001384279999001592,
"count": 1,
"self": 0.0001384279999001592,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 587.8975593209802,
"count": 601778,
"is_parallel": true,
"self": 13.886148590927405,
"children": {
"process_trajectory": {
"total": 317.6449204460522,
"count": 601778,
"is_parallel": true,
"self": 315.68420523105203,
"children": {
"RLTrainer._checkpoint": {
"total": 1.9607152150001639,
"count": 4,
"is_parallel": true,
"self": 1.9607152150001639
}
}
},
"_update_policy": {
"total": 256.36649028400063,
"count": 90,
"is_parallel": true,
"self": 89.41042703999426,
"children": {
"TorchPPOOptimizer.update": {
"total": 166.95606324400637,
"count": 4587,
"is_parallel": true,
"self": 166.95606324400637
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15518807000012202,
"count": 1,
"self": 0.0011124160002964345,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1540756539998256,
"count": 1,
"self": 0.1540756539998256
}
}
}
}
}
}
}