davidkh's picture
First Push
1344c55 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7170922160148621,
"min": 0.7170922160148621,
"max": 2.862549304962158,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6854.6845703125,
"min": 6854.6845703125,
"max": 29504.296875,
"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": 12.96528148651123,
"min": 0.40033575892448425,
"max": 12.96528148651123,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.22998046875,
"min": 77.6651382446289,
"max": 2644.1513671875,
"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": 0.07426085522884558,
"min": 0.0614241903073693,
"max": 0.07587313487002736,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29704342091538233,
"min": 0.2587231445411853,
"max": 0.37349915278701146,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17292260656169814,
"min": 0.11044267012609862,
"max": 0.2755002590955472,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6916904262467926,
"min": 0.4417706805043945,
"max": 1.3775012954777361,
"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": 3.0681818181818183,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 135.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.0681818181818183,
"max": 25.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 135.0,
"max": 1428.0,
"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": "1722506784",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722507234"
},
"total": 449.4131349669999,
"count": 1,
"self": 0.4386234409996632,
"children": {
"run_training.setup": {
"total": 0.07883208000021114,
"count": 1,
"self": 0.07883208000021114
},
"TrainerController.start_learning": {
"total": 448.89567944600003,
"count": 1,
"self": 0.5484178790022725,
"children": {
"TrainerController._reset_env": {
"total": 2.467464588999974,
"count": 1,
"self": 2.467464588999974
},
"TrainerController.advance": {
"total": 445.78379056599783,
"count": 18202,
"self": 0.2658705709870901,
"children": {
"env_step": {
"total": 445.51791999501074,
"count": 18202,
"self": 288.44413525204436,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.80064510597413,
"count": 18202,
"self": 1.4528314079434494,
"children": {
"TorchPolicy.evaluate": {
"total": 155.34781369803068,
"count": 18202,
"self": 155.34781369803068
}
}
},
"workers": {
"total": 0.27313963699225496,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 447.70790564700997,
"count": 18202,
"is_parallel": true,
"self": 227.72243573901096,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005718587999808733,
"count": 1,
"is_parallel": true,
"self": 0.004031983000004402,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016866049998043309,
"count": 10,
"is_parallel": true,
"self": 0.0016866049998043309
}
}
},
"UnityEnvironment.step": {
"total": 0.03795704399999522,
"count": 1,
"is_parallel": true,
"self": 0.000828483999839591,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004036999998788815,
"count": 1,
"is_parallel": true,
"self": 0.0004036999998788815
},
"communicator.exchange": {
"total": 0.03453027600016867,
"count": 1,
"is_parallel": true,
"self": 0.03453027600016867
},
"steps_from_proto": {
"total": 0.0021945840001080796,
"count": 1,
"is_parallel": true,
"self": 0.0004303519999666605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017642320001414191,
"count": 10,
"is_parallel": true,
"self": 0.0017642320001414191
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.985469907999,
"count": 18201,
"is_parallel": true,
"self": 10.006043974035038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.337707151984887,
"count": 18201,
"is_parallel": true,
"self": 5.337707151984887
},
"communicator.exchange": {
"total": 171.40227279298688,
"count": 18201,
"is_parallel": true,
"self": 171.40227279298688
},
"steps_from_proto": {
"total": 33.2394459889922,
"count": 18201,
"is_parallel": true,
"self": 6.255921607974187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.983524381018015,
"count": 182010,
"is_parallel": true,
"self": 26.983524381018015
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001877140000487998,
"count": 1,
"self": 0.0001877140000487998,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.1531201829939,
"count": 656817,
"is_parallel": true,
"self": 13.923575852079011,
"children": {
"process_trajectory": {
"total": 243.44339684291594,
"count": 656817,
"is_parallel": true,
"self": 242.50012270791603,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9432741349999105,
"count": 4,
"is_parallel": true,
"self": 0.9432741349999105
}
}
},
"_update_policy": {
"total": 182.78614748799896,
"count": 90,
"is_parallel": true,
"self": 57.39645956099548,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.38968792700348,
"count": 4587,
"is_parallel": true,
"self": 125.38968792700348
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09581869799990272,
"count": 1,
"self": 0.0010112569998455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09480744100005722,
"count": 1,
"self": 0.09480744100005722
}
}
}
}
}
}
}