kjamesh's picture
First Push
bbe5139 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8235166668891907,
"min": 0.8235166668891907,
"max": 2.876037836074829,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7871.99560546875,
"min": 7871.99560546875,
"max": 29485.140625,
"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": 12.828970909118652,
"min": 0.38668957352638245,
"max": 12.828970909118652,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.6494140625,
"min": 75.01777648925781,
"max": 2598.506103515625,
"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": 0.07189294106530153,
"min": 0.061271651754413695,
"max": 0.07678465140828242,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2875717642612061,
"min": 0.24508660701765478,
"max": 0.3839232570414121,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20673519117282887,
"min": 0.13115035084774718,
"max": 0.2875338496238578,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8269407646913155,
"min": 0.5246014033909887,
"max": 1.3606984057262832,
"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": 25.386363636363637,
"min": 3.477272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 153.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.477272727272727,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 153.0,
"max": 1394.0,
"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": "1747278637",
"python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]",
"command_line_arguments": "/home/gym/.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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747278846"
},
"total": 209.08536911400006,
"count": 1,
"self": 0.1665667730012501,
"children": {
"run_training.setup": {
"total": 0.011554828999578604,
"count": 1,
"self": 0.011554828999578604
},
"TrainerController.start_learning": {
"total": 208.90724751199923,
"count": 1,
"self": 0.27059547705175646,
"children": {
"TrainerController._reset_env": {
"total": 0.7372551119988202,
"count": 1,
"self": 0.7372551119988202
},
"TrainerController.advance": {
"total": 207.87102784394847,
"count": 18202,
"self": 0.11626730369607685,
"children": {
"env_step": {
"total": 207.7547605402524,
"count": 18202,
"self": 167.03257203322391,
"children": {
"SubprocessEnvManager._take_step": {
"total": 40.59824595797363,
"count": 18202,
"self": 0.5934705529489293,
"children": {
"TorchPolicy.evaluate": {
"total": 40.0047754050247,
"count": 18202,
"self": 40.0047754050247
}
}
},
"workers": {
"total": 0.12394254905484559,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 208.39984192004886,
"count": 18202,
"is_parallel": true,
"self": 74.47709172192663,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002704773000004934,
"count": 1,
"is_parallel": true,
"self": 0.002051337998636882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006534350013680523,
"count": 10,
"is_parallel": true,
"self": 0.0006534350013680523
}
}
},
"UnityEnvironment.step": {
"total": 0.013530636999348644,
"count": 1,
"is_parallel": true,
"self": 0.00014030899910721928,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00010872500024561305,
"count": 1,
"is_parallel": true,
"self": 0.00010872500024561305
},
"communicator.exchange": {
"total": 0.012872916000560508,
"count": 1,
"is_parallel": true,
"self": 0.012872916000560508
},
"steps_from_proto": {
"total": 0.00040868699943530373,
"count": 1,
"is_parallel": true,
"self": 9.252799645764753e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003161590029776562,
"count": 10,
"is_parallel": true,
"self": 0.0003161590029776562
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 133.92275019812223,
"count": 18201,
"is_parallel": true,
"self": 2.6647822050181276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.6686047229177348,
"count": 18201,
"is_parallel": true,
"self": 1.6686047229177348
},
"communicator.exchange": {
"total": 121.61326282303708,
"count": 18201,
"is_parallel": true,
"self": 121.61326282303708
},
"steps_from_proto": {
"total": 7.9761004471492924,
"count": 18201,
"is_parallel": true,
"self": 1.7415394210402155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.234561026109077,
"count": 182010,
"is_parallel": true,
"self": 6.234561026109077
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.648000039102044e-05,
"count": 1,
"self": 8.648000039102044e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 206.91423761374244,
"count": 233172,
"is_parallel": true,
"self": 2.923419029702927,
"children": {
"process_trajectory": {
"total": 118.89350930504224,
"count": 233172,
"is_parallel": true,
"self": 118.65521503304444,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23829427199780184,
"count": 4,
"is_parallel": true,
"self": 0.23829427199780184
}
}
},
"_update_policy": {
"total": 85.09730927899727,
"count": 90,
"is_parallel": true,
"self": 13.442406189946269,
"children": {
"TorchPPOOptimizer.update": {
"total": 71.654903089051,
"count": 4587,
"is_parallel": true,
"self": 71.654903089051
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.028282598999794573,
"count": 1,
"self": 0.0004725679991679499,
"children": {
"RLTrainer._checkpoint": {
"total": 0.027810031000626623,
"count": 1,
"self": 0.027810031000626623
}
}
}
}
}
}
}