johnx4321's picture
First Push
ca3ccb2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8790844082832336,
"min": 0.8515345454216003,
"max": 2.817441701889038,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8354.818359375,
"min": 8238.962890625,
"max": 28760.4453125,
"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": 12.833203315734863,
"min": 0.373249888420105,
"max": 12.833203315734863,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2502.474609375,
"min": 72.41047668457031,
"max": 2608.00439453125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0731671676402067,
"min": 0.06088406611930158,
"max": 0.0732357677288568,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2926686705608268,
"min": 0.26332025795030256,
"max": 0.35772802402475373,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21729009580232347,
"min": 0.12430329288826232,
"max": 0.31187827731756607,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8691603832092939,
"min": 0.4972131715530493,
"max": 1.274809935221485,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.795454545454547,
"min": 3.25,
"max": 25.327272727272728,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 143.0,
"max": 1393.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 3.25,
"max": 25.327272727272728,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 143.0,
"max": 1393.0,
"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": "1767314440",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1767314886"
},
"total": 446.273692946,
"count": 1,
"self": 0.44451189699998395,
"children": {
"run_training.setup": {
"total": 0.026565088000097603,
"count": 1,
"self": 0.026565088000097603
},
"TrainerController.start_learning": {
"total": 445.8026159609999,
"count": 1,
"self": 0.357303584989495,
"children": {
"TrainerController._reset_env": {
"total": 3.656509568999809,
"count": 1,
"self": 3.656509568999809
},
"TrainerController.advance": {
"total": 441.6981404770106,
"count": 18192,
"self": 0.3644826040213047,
"children": {
"env_step": {
"total": 322.41458879098127,
"count": 18192,
"self": 251.6896371420089,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.50907287798327,
"count": 18192,
"self": 1.2652937179843775,
"children": {
"TorchPolicy.evaluate": {
"total": 69.2437791599989,
"count": 18192,
"self": 69.2437791599989
}
}
},
"workers": {
"total": 0.21587877098909303,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.0736827770195,
"count": 18192,
"is_parallel": true,
"self": 222.9212007280198,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005510416000106488,
"count": 1,
"is_parallel": true,
"self": 0.004026258999829224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014841570002772642,
"count": 10,
"is_parallel": true,
"self": 0.0014841570002772642
}
}
},
"UnityEnvironment.step": {
"total": 0.06296947900000305,
"count": 1,
"is_parallel": true,
"self": 0.0005905579998852772,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036813100018662226,
"count": 1,
"is_parallel": true,
"self": 0.00036813100018662226
},
"communicator.exchange": {
"total": 0.0547191359999033,
"count": 1,
"is_parallel": true,
"self": 0.0547191359999033
},
"steps_from_proto": {
"total": 0.007291654000027847,
"count": 1,
"is_parallel": true,
"self": 0.003426661000275999,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038649929997518484,
"count": 10,
"is_parallel": true,
"self": 0.0038649929997518484
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.15248204899967,
"count": 18191,
"is_parallel": true,
"self": 10.465083979994233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.666321676000507,
"count": 18191,
"is_parallel": true,
"self": 5.666321676000507
},
"communicator.exchange": {
"total": 167.6359709859962,
"count": 18191,
"is_parallel": true,
"self": 167.6359709859962
},
"steps_from_proto": {
"total": 37.38510540700872,
"count": 18191,
"is_parallel": true,
"self": 6.721215291950557,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.663890115058166,
"count": 181910,
"is_parallel": true,
"self": 30.663890115058166
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.91906908200804,
"count": 18192,
"self": 0.42345349400670784,
"children": {
"process_trajectory": {
"total": 26.609934758001145,
"count": 18192,
"self": 26.106167510001114,
"children": {
"RLTrainer._checkpoint": {
"total": 0.503767248000031,
"count": 4,
"self": 0.503767248000031
}
}
},
"_update_policy": {
"total": 91.88568083000018,
"count": 90,
"self": 37.70181427901002,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.18386655099016,
"count": 4587,
"self": 54.18386655099016
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2600000900420127e-06,
"count": 1,
"self": 1.2600000900420127e-06
},
"TrainerController._save_models": {
"total": 0.09066106999989643,
"count": 1,
"self": 0.0007227469998269953,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08993832300006943,
"count": 1,
"self": 0.08993832300006943
}
}
}
}
}
}
}