Pengcheng-Wang's picture
First Push
ffe397a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.08721923828125,
"min": 1.0198920965194702,
"max": 2.861902952194214,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10428.607421875,
"min": 9959.0185546875,
"max": 29371.7109375,
"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": 12.2214994430542,
"min": 0.2775755822658539,
"max": 12.2214994430542,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2383.1923828125,
"min": 53.84966278076172,
"max": 2439.70361328125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06752264493686608,
"min": 0.061979142628957096,
"max": 0.07389007019790407,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2700905797474643,
"min": 0.25776363534033386,
"max": 0.36945035098952034,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20163605807750834,
"min": 0.09816836857113659,
"max": 0.2845078771751301,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8065442323100334,
"min": 0.39267347428454635,
"max": 1.3955366474156286,
"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": 24.681818181818183,
"min": 2.840909090909091,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 125.0,
"max": 1326.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 2.840909090909091,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 125.0,
"max": 1326.0,
"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": "1723157660",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723158319"
},
"total": 658.459800094,
"count": 1,
"self": 1.0221044130000791,
"children": {
"run_training.setup": {
"total": 0.10830854000005274,
"count": 1,
"self": 0.10830854000005274
},
"TrainerController.start_learning": {
"total": 657.3293871409999,
"count": 1,
"self": 0.9830568359841436,
"children": {
"TrainerController._reset_env": {
"total": 5.531484882999848,
"count": 1,
"self": 5.531484882999848
},
"TrainerController.advance": {
"total": 650.6659602990158,
"count": 18209,
"self": 0.5049237719954363,
"children": {
"env_step": {
"total": 650.1610365270203,
"count": 18209,
"self": 500.59156205401246,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.086763571009,
"count": 18209,
"self": 2.932131324022521,
"children": {
"TorchPolicy.evaluate": {
"total": 146.15463224698647,
"count": 18209,
"self": 146.15463224698647
}
}
},
"workers": {
"total": 0.4827109019988711,
"count": 18209,
"self": 0.0,
"children": {
"worker_root": {
"total": 654.9849199100154,
"count": 18209,
"is_parallel": true,
"self": 308.53403643100773,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009129185000119833,
"count": 1,
"is_parallel": true,
"self": 0.005339216999800556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003789968000319277,
"count": 10,
"is_parallel": true,
"self": 0.003789968000319277
}
}
},
"UnityEnvironment.step": {
"total": 0.04831082000009701,
"count": 1,
"is_parallel": true,
"self": 0.0008918840001115313,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047173299981295713,
"count": 1,
"is_parallel": true,
"self": 0.00047173299981295713
},
"communicator.exchange": {
"total": 0.04409640800008674,
"count": 1,
"is_parallel": true,
"self": 0.04409640800008674
},
"steps_from_proto": {
"total": 0.002850795000085782,
"count": 1,
"is_parallel": true,
"self": 0.0005662680002842535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022845269998015283,
"count": 10,
"is_parallel": true,
"self": 0.0022845269998015283
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 346.45088347900764,
"count": 18208,
"is_parallel": true,
"self": 16.56157143001701,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.257028462998278,
"count": 18208,
"is_parallel": true,
"self": 8.257028462998278
},
"communicator.exchange": {
"total": 273.0022301660051,
"count": 18208,
"is_parallel": true,
"self": 273.0022301660051
},
"steps_from_proto": {
"total": 48.630053419987235,
"count": 18208,
"is_parallel": true,
"self": 9.8472051820047,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.782848237982535,
"count": 182080,
"is_parallel": true,
"self": 38.782848237982535
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00026900700004262035,
"count": 1,
"self": 0.00026900700004262035,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 643.1599926519034,
"count": 778731,
"is_parallel": true,
"self": 19.65601793690962,
"children": {
"process_trajectory": {
"total": 355.8835372629935,
"count": 778731,
"is_parallel": true,
"self": 354.76466062499344,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1188766380000743,
"count": 4,
"is_parallel": true,
"self": 1.1188766380000743
}
}
},
"_update_policy": {
"total": 267.62043745200026,
"count": 90,
"is_parallel": true,
"self": 73.85685167501015,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.7635857769901,
"count": 4587,
"is_parallel": true,
"self": 193.7635857769901
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14861611600008473,
"count": 1,
"self": 0.0016935600001488638,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14692255599993587,
"count": 1,
"self": 0.14692255599993587
}
}
}
}
}
}
}