RafeDolan's picture
First SB agent
c4926ed verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.000296950340271,
"min": 1.000296950340271,
"max": 2.871333599090576,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9561.8388671875,
"min": 9561.8388671875,
"max": 29500.08203125,
"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": 12.922435760498047,
"min": 0.3303082585334778,
"max": 12.922435760498047,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.875,
"min": 64.07980346679688,
"max": 2623.760986328125,
"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": 0.06895607073095686,
"min": 0.06496840099000609,
"max": 0.07354754099608674,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27582428292382744,
"min": 0.2603330122322351,
"max": 0.36204203049476513,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19381386669827444,
"min": 0.12579687094251973,
"max": 0.286003506358932,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7752554667930978,
"min": 0.5031874837700789,
"max": 1.4230957168574427,
"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": 25.477272727272727,
"min": 3.227272727272727,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 142.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.227272727272727,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 142.0,
"max": 1396.0,
"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": "1765818006",
"python_version": "3.10.12 (main, Oct 23 2025, 20:12:04) [GCC 13.3.0]",
"command_line_arguments": "/home/rafe/Repositories/Hugging-Face-Courses/HF-venv-5/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetRafe --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": "1765819134"
},
"total": 1128.2102341329955,
"count": 1,
"self": 0.425520755990874,
"children": {
"run_training.setup": {
"total": 0.026566419001028407,
"count": 1,
"self": 0.026566419001028407
},
"TrainerController.start_learning": {
"total": 1127.7581469580036,
"count": 1,
"self": 1.5793370217943448,
"children": {
"TrainerController._reset_env": {
"total": 3.1321786569969845,
"count": 1,
"self": 3.1321786569969845
},
"TrainerController.advance": {
"total": 1122.892440676209,
"count": 18204,
"self": 0.7220235580243752,
"children": {
"env_step": {
"total": 1122.1704171181846,
"count": 18204,
"self": 816.4613591552916,
"children": {
"SubprocessEnvManager._take_step": {
"total": 304.9674491199112,
"count": 18204,
"self": 4.085182632799842,
"children": {
"TorchPolicy.evaluate": {
"total": 300.88226648711134,
"count": 18204,
"self": 300.88226648711134
}
}
},
"workers": {
"total": 0.7416088429818046,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 1125.2327860727528,
"count": 18204,
"is_parallel": true,
"self": 475.6064477983309,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025411710012122057,
"count": 1,
"is_parallel": true,
"self": 0.0007024939986877143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018386770025244914,
"count": 10,
"is_parallel": true,
"self": 0.0018386770025244914
}
}
},
"UnityEnvironment.step": {
"total": 0.051240457003586926,
"count": 1,
"is_parallel": true,
"self": 0.0006040239968569949,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006972550036152825,
"count": 1,
"is_parallel": true,
"self": 0.0006972550036152825
},
"communicator.exchange": {
"total": 0.04818461499962723,
"count": 1,
"is_parallel": true,
"self": 0.04818461499962723
},
"steps_from_proto": {
"total": 0.0017545630034874193,
"count": 1,
"is_parallel": true,
"self": 0.0003812340146396309,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013733289888477884,
"count": 10,
"is_parallel": true,
"self": 0.0013733289888477884
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 649.6263382744219,
"count": 18203,
"is_parallel": true,
"self": 23.647262344624323,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 15.423294898595486,
"count": 18203,
"is_parallel": true,
"self": 15.423294898595486
},
"communicator.exchange": {
"total": 532.6247725674475,
"count": 18203,
"is_parallel": true,
"self": 532.6247725674475
},
"steps_from_proto": {
"total": 77.93100846375455,
"count": 18203,
"is_parallel": true,
"self": 15.316856631892733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.61415183186182,
"count": 182030,
"is_parallel": true,
"self": 62.61415183186182
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003796559976763092,
"count": 1,
"self": 0.0003796559976763092,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1117.3745578452508,
"count": 363573,
"is_parallel": true,
"self": 16.2441037131357,
"children": {
"process_trajectory": {
"total": 580.6587541891349,
"count": 363573,
"is_parallel": true,
"self": 579.0511374541384,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6076167349965544,
"count": 4,
"is_parallel": true,
"self": 1.6076167349965544
}
}
},
"_update_policy": {
"total": 520.4716999429802,
"count": 90,
"is_parallel": true,
"self": 120.7901798288367,
"children": {
"TorchPPOOptimizer.update": {
"total": 399.6815201141435,
"count": 4587,
"is_parallel": true,
"self": 399.6815201141435
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1538109470056952,
"count": 1,
"self": 0.001071895007044077,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15273905199865112,
"count": 1,
"self": 0.15273905199865112
}
}
}
}
}
}
}