alexchilton's picture
First Push
c81a377 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9777206778526306,
"min": 0.9777206778526306,
"max": 2.864017963409424,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9367.5419921875,
"min": 9367.5419921875,
"max": 29361.912109375,
"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": 12.871161460876465,
"min": 0.3498232364654541,
"max": 12.886719703674316,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2509.87646484375,
"min": 67.86570739746094,
"max": 2628.890869140625,
"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": 0.07211549415546423,
"min": 0.06298021136781778,
"max": 0.07270903376218699,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2884619766218569,
"min": 0.25192084547127114,
"max": 0.3635451688109349,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1898511301580013,
"min": 0.10393637203036205,
"max": 0.2920163093828687,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7594045206320053,
"min": 0.4157454881214482,
"max": 1.4600815469143436,
"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": 24.954545454545453,
"min": 3.272727272727273,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 144.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.272727272727273,
"max": 25.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 144.0,
"max": 1389.0,
"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": "1718112321",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yml --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": "1718112904"
},
"total": 583.678076778,
"count": 1,
"self": 0.7642036039999311,
"children": {
"run_training.setup": {
"total": 0.10143641399997705,
"count": 1,
"self": 0.10143641399997705
},
"TrainerController.start_learning": {
"total": 582.8124367600001,
"count": 1,
"self": 0.7924819350079133,
"children": {
"TrainerController._reset_env": {
"total": 3.6838521390000096,
"count": 1,
"self": 3.6838521390000096
},
"TrainerController.advance": {
"total": 578.2277195429923,
"count": 18204,
"self": 0.4228700339978104,
"children": {
"env_step": {
"total": 577.8048495089945,
"count": 18204,
"self": 447.5056474799935,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.89160212599552,
"count": 18204,
"self": 2.2645040840003503,
"children": {
"TorchPolicy.evaluate": {
"total": 127.62709804199517,
"count": 18204,
"self": 127.62709804199517
}
}
},
"workers": {
"total": 0.4075999030054618,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 580.7887591850088,
"count": 18204,
"is_parallel": true,
"self": 271.36262019301273,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009433949000026587,
"count": 1,
"is_parallel": true,
"self": 0.003957676000140964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005476272999885623,
"count": 10,
"is_parallel": true,
"self": 0.005476272999885623
}
}
},
"UnityEnvironment.step": {
"total": 0.042285604000085186,
"count": 1,
"is_parallel": true,
"self": 0.0008440430001428467,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004756680000355118,
"count": 1,
"is_parallel": true,
"self": 0.0004756680000355118
},
"communicator.exchange": {
"total": 0.03851739199990334,
"count": 1,
"is_parallel": true,
"self": 0.03851739199990334
},
"steps_from_proto": {
"total": 0.002448501000003489,
"count": 1,
"is_parallel": true,
"self": 0.0004681949998257551,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001980306000177734,
"count": 10,
"is_parallel": true,
"self": 0.001980306000177734
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 309.426138991996,
"count": 18203,
"is_parallel": true,
"self": 14.844734389992823,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.549140370992404,
"count": 18203,
"is_parallel": true,
"self": 7.549140370992404
},
"communicator.exchange": {
"total": 242.86388122601954,
"count": 18203,
"is_parallel": true,
"self": 242.86388122601954
},
"steps_from_proto": {
"total": 44.168383004991256,
"count": 18203,
"is_parallel": true,
"self": 8.64627604301279,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.522106961978466,
"count": 182030,
"is_parallel": true,
"self": 35.522106961978466
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001617049999822484,
"count": 1,
"self": 0.0001617049999822484,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 571.4851954571026,
"count": 763912,
"is_parallel": true,
"self": 17.17117811712376,
"children": {
"process_trajectory": {
"total": 312.7212898009785,
"count": 763912,
"is_parallel": true,
"self": 311.7786102779786,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9426795229999243,
"count": 4,
"is_parallel": true,
"self": 0.9426795229999243
}
}
},
"_update_policy": {
"total": 241.5927275390003,
"count": 90,
"is_parallel": true,
"self": 69.26448929700405,
"children": {
"TorchPPOOptimizer.update": {
"total": 172.32823824199625,
"count": 4587,
"is_parallel": true,
"self": 172.32823824199625
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10822143799987316,
"count": 1,
"self": 0.0013837709998369974,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10683766700003616,
"count": 1,
"self": 0.10683766700003616
}
}
}
}
}
}
}