Wilbur1240's picture
First Push
ccf1e11 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8000240921974182,
"min": 0.8000240921974182,
"max": 2.8548882007598877,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7603.42919921875,
"min": 7603.42919921875,
"max": 29142.69921875,
"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": 12.951210975646973,
"min": 0.3905879855155945,
"max": 12.951210975646973,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2525.486083984375,
"min": 75.7740707397461,
"max": 2619.76171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06848385888155034,
"min": 0.06138451122262232,
"max": 0.07915881412998574,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27393543552620137,
"min": 0.2599319975793775,
"max": 0.39579407064992866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21405046356513222,
"min": 0.13331603786026985,
"max": 0.30163818364049877,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8562018542605289,
"min": 0.5332641514410794,
"max": 1.4063858419072393,
"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": 25.704545454545453,
"min": 3.590909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 158.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.590909090909091,
"max": 25.84090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 158.0,
"max": 1399.0,
"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": "1750056855",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750057281"
},
"total": 425.45152086999997,
"count": 1,
"self": 0.7516185700000051,
"children": {
"run_training.setup": {
"total": 0.02259885099999792,
"count": 1,
"self": 0.02259885099999792
},
"TrainerController.start_learning": {
"total": 424.67730344899996,
"count": 1,
"self": 0.35557755902118515,
"children": {
"TrainerController._reset_env": {
"total": 3.3423415820000173,
"count": 1,
"self": 3.3423415820000173
},
"TrainerController.advance": {
"total": 420.8535376389789,
"count": 18192,
"self": 0.37316092498758735,
"children": {
"env_step": {
"total": 302.88068657100064,
"count": 18192,
"self": 232.52237059900847,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.1510997219874,
"count": 18192,
"self": 1.254127097981609,
"children": {
"TorchPolicy.evaluate": {
"total": 68.8969726240058,
"count": 18192,
"self": 68.8969726240058
}
}
},
"workers": {
"total": 0.20721625000476251,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.1618665080081,
"count": 18192,
"is_parallel": true,
"self": 218.88717543803216,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004843285999982072,
"count": 1,
"is_parallel": true,
"self": 0.003365542000096866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001477743999885206,
"count": 10,
"is_parallel": true,
"self": 0.001477743999885206
}
}
},
"UnityEnvironment.step": {
"total": 0.0703464170001098,
"count": 1,
"is_parallel": true,
"self": 0.0006132729999990261,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039525400006823475,
"count": 1,
"is_parallel": true,
"self": 0.00039525400006823475
},
"communicator.exchange": {
"total": 0.06730188200003795,
"count": 1,
"is_parallel": true,
"self": 0.06730188200003795
},
"steps_from_proto": {
"total": 0.0020360080000045855,
"count": 1,
"is_parallel": true,
"self": 0.0004165719998354689,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016194360001691166,
"count": 10,
"is_parallel": true,
"self": 0.0016194360001691166
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.27469106997592,
"count": 18191,
"is_parallel": true,
"self": 9.821024892950732,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.440974874004382,
"count": 18191,
"is_parallel": true,
"self": 5.440974874004382
},
"communicator.exchange": {
"total": 156.95900082301557,
"count": 18191,
"is_parallel": true,
"self": 156.95900082301557
},
"steps_from_proto": {
"total": 32.05369048000523,
"count": 18191,
"is_parallel": true,
"self": 5.7235855220051235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.330104958000106,
"count": 181910,
"is_parallel": true,
"self": 26.330104958000106
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.59969014299065,
"count": 18192,
"self": 0.43383800299272934,
"children": {
"process_trajectory": {
"total": 26.316537225997877,
"count": 18192,
"self": 25.887223833997723,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4293133920001537,
"count": 4,
"self": 0.4293133920001537
}
}
},
"_update_policy": {
"total": 90.84931491400005,
"count": 90,
"self": 37.195315922005875,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.65399899199417,
"count": 4587,
"self": 53.65399899199417
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3490000583260553e-06,
"count": 1,
"self": 1.3490000583260553e-06
},
"TrainerController._save_models": {
"total": 0.12584531999982573,
"count": 1,
"self": 0.0011276309999175282,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1247176889999082,
"count": 1,
"self": 0.1247176889999082
}
}
}
}
}
}
}