GustavoDLRA's picture
First Push
5f77380 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8511422276496887,
"min": 0.8511422276496887,
"max": 2.854546070098877,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8089.255859375,
"min": 8089.255859375,
"max": 29139.205078125,
"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": 13.004329681396484,
"min": 0.3205580711364746,
"max": 13.004329681396484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2535.84423828125,
"min": 62.188262939453125,
"max": 2639.0087890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06873861883493601,
"min": 0.059891020053456645,
"max": 0.07594121184806948,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27495447533974404,
"min": 0.2446527390474883,
"max": 0.3640110739757873,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2233740030696579,
"min": 0.11784781501331713,
"max": 0.2566952370107174,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8934960122786316,
"min": 0.47139126005326853,
"max": 1.2684447701070822,
"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": 25.045454545454547,
"min": 3.159090909090909,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 139.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.159090909090909,
"max": 25.89090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 139.0,
"max": 1424.0,
"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": "1762756318",
"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 --force",
"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": "1762756794"
},
"total": 476.0240158800002,
"count": 1,
"self": 0.6378222170001209,
"children": {
"run_training.setup": {
"total": 0.03936030100021526,
"count": 1,
"self": 0.03936030100021526
},
"TrainerController.start_learning": {
"total": 475.34683336199987,
"count": 1,
"self": 0.3781092139715838,
"children": {
"TrainerController._reset_env": {
"total": 4.720136015999742,
"count": 1,
"self": 4.720136015999742
},
"TrainerController.advance": {
"total": 470.1087630650286,
"count": 18192,
"self": 0.40176974805081045,
"children": {
"env_step": {
"total": 345.0801019879864,
"count": 18192,
"self": 271.2102361139837,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.64175464399159,
"count": 18192,
"self": 1.3423382180171757,
"children": {
"TorchPolicy.evaluate": {
"total": 72.29941642597441,
"count": 18192,
"self": 72.29941642597441
}
}
},
"workers": {
"total": 0.228111230011109,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 472.9418100690168,
"count": 18192,
"is_parallel": true,
"self": 234.88047401097947,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003076802999657957,
"count": 1,
"is_parallel": true,
"self": 0.0008376380001209327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022391649995370244,
"count": 10,
"is_parallel": true,
"self": 0.0022391649995370244
}
}
},
"UnityEnvironment.step": {
"total": 0.036572337999587035,
"count": 1,
"is_parallel": true,
"self": 0.0006232089990589884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041628200006016414,
"count": 1,
"is_parallel": true,
"self": 0.00041628200006016414
},
"communicator.exchange": {
"total": 0.033589366000342125,
"count": 1,
"is_parallel": true,
"self": 0.033589366000342125
},
"steps_from_proto": {
"total": 0.0019434810001257574,
"count": 1,
"is_parallel": true,
"self": 0.0004064059999109304,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001537075000214827,
"count": 10,
"is_parallel": true,
"self": 0.001537075000214827
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.06133605803734,
"count": 18191,
"is_parallel": true,
"self": 10.471189429093101,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6074874799728605,
"count": 18191,
"is_parallel": true,
"self": 5.6074874799728605
},
"communicator.exchange": {
"total": 181.77146322696944,
"count": 18191,
"is_parallel": true,
"self": 181.77146322696944
},
"steps_from_proto": {
"total": 40.211195922001934,
"count": 18191,
"is_parallel": true,
"self": 7.27685318704016,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.934342734961774,
"count": 181910,
"is_parallel": true,
"self": 32.934342734961774
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.6268913289914,
"count": 18192,
"self": 0.47888136197434505,
"children": {
"process_trajectory": {
"total": 29.061165731014626,
"count": 18192,
"self": 28.48523093001495,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5759348009996756,
"count": 4,
"self": 0.5759348009996756
}
}
},
"_update_policy": {
"total": 95.08684423600243,
"count": 90,
"self": 39.06526255399558,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.021581682006854,
"count": 4587,
"self": 56.021581682006854
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.099999260797631e-07,
"count": 1,
"self": 9.099999260797631e-07
},
"TrainerController._save_models": {
"total": 0.13982415700002093,
"count": 1,
"self": 0.010466385000199807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12935777199982113,
"count": 1,
"self": 0.12935777199982113
}
}
}
}
}
}
}