Alexander Mooney
First Push
45c11ec verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9117463231086731,
"min": 0.9117463231086731,
"max": 2.8306257724761963,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8665.2373046875,
"min": 8665.2373046875,
"max": 28895.02734375,
"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": 12.860331535339355,
"min": 0.43526679277420044,
"max": 12.860331535339355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.7646484375,
"min": 84.44175720214844,
"max": 2577.19970703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06663884143385004,
"min": 0.06512310578345064,
"max": 0.07821485108191457,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2665553657354002,
"min": 0.26049242313380255,
"max": 0.3788540816338568,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1769714219970446,
"min": 0.11726557316062242,
"max": 0.26513844424603034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7078856879881784,
"min": 0.46906229264248966,
"max": 1.3256922212301516,
"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": 25.90909090909091,
"min": 3.522727272727273,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 155.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.522727272727273,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 155.0,
"max": 1387.0,
"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": "1743019286",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743019912"
},
"total": 626.1476563260001,
"count": 1,
"self": 0.6044956740004181,
"children": {
"run_training.setup": {
"total": 0.04886492899981931,
"count": 1,
"self": 0.04886492899981931
},
"TrainerController.start_learning": {
"total": 625.4942957229998,
"count": 1,
"self": 0.7195988979813137,
"children": {
"TrainerController._reset_env": {
"total": 5.099920430000111,
"count": 1,
"self": 5.099920430000111
},
"TrainerController.advance": {
"total": 619.5854398480187,
"count": 18192,
"self": 0.7305845340190444,
"children": {
"env_step": {
"total": 428.395553666006,
"count": 18192,
"self": 364.5503025230478,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.441736264975816,
"count": 18192,
"self": 2.616025716979493,
"children": {
"TorchPolicy.evaluate": {
"total": 60.82571054799632,
"count": 18192,
"self": 60.82571054799632
}
}
},
"workers": {
"total": 0.4035148779823885,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 623.0997321239643,
"count": 18192,
"is_parallel": true,
"self": 309.690545527978,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011793678999993062,
"count": 1,
"is_parallel": true,
"self": 0.008151527000109127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003642151999883936,
"count": 10,
"is_parallel": true,
"self": 0.003642151999883936
}
}
},
"UnityEnvironment.step": {
"total": 0.0573966780000319,
"count": 1,
"is_parallel": true,
"self": 0.0007878110002366157,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00056485100003556,
"count": 1,
"is_parallel": true,
"self": 0.00056485100003556
},
"communicator.exchange": {
"total": 0.05383796999990409,
"count": 1,
"is_parallel": true,
"self": 0.05383796999990409
},
"steps_from_proto": {
"total": 0.0022060459998556325,
"count": 1,
"is_parallel": true,
"self": 0.0004177750001872482,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017882709996683843,
"count": 10,
"is_parallel": true,
"self": 0.0017882709996683843
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 313.4091865959863,
"count": 18191,
"is_parallel": true,
"self": 14.963252220969252,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.03581477000921,
"count": 18191,
"is_parallel": true,
"self": 8.03581477000921
},
"communicator.exchange": {
"total": 245.00326659599477,
"count": 18191,
"is_parallel": true,
"self": 245.00326659599477
},
"steps_from_proto": {
"total": 45.40685300901305,
"count": 18191,
"is_parallel": true,
"self": 9.051554638106381,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.35529837090667,
"count": 181910,
"is_parallel": true,
"self": 36.35529837090667
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 190.4593016479937,
"count": 18192,
"self": 1.0021804570126278,
"children": {
"process_trajectory": {
"total": 36.46118995298252,
"count": 18192,
"self": 35.859654532982404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6015354200001184,
"count": 4,
"self": 0.6015354200001184
}
}
},
"_update_policy": {
"total": 152.99593123799855,
"count": 90,
"self": 55.45184915398727,
"children": {
"TorchPPOOptimizer.update": {
"total": 97.54408208401128,
"count": 4587,
"self": 97.54408208401128
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0869998732232489e-06,
"count": 1,
"self": 1.0869998732232489e-06
},
"TrainerController._save_models": {
"total": 0.08933545999980197,
"count": 1,
"self": 0.0013028759999542672,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0880325839998477,
"count": 1,
"self": 0.0880325839998477
}
}
}
}
}
}
}