Mitchell0528's picture
First Push
026fb8b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8603359460830688,
"min": 0.8603359460830688,
"max": 2.8775343894958496,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8176.6328125,
"min": 8176.6328125,
"max": 29373.87109375,
"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": 13.165454864501953,
"min": 0.14595341682434082,
"max": 13.219054222106934,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2567.263671875,
"min": 28.31496238708496,
"max": 2696.68701171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07336530811609883,
"min": 0.06164126711208191,
"max": 0.07715635897657908,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2934612324643953,
"min": 0.2587208980916972,
"max": 0.36921577959312313,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1852540351523488,
"min": 0.1064229131705931,
"max": 0.26333556233667854,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7410161406093952,
"min": 0.4256916526823724,
"max": 1.3166778116833928,
"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": 25.545454545454547,
"min": 2.9318181818181817,
"max": 26.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 129.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 2.9318181818181817,
"max": 26.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 129.0,
"max": 1416.0,
"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": "1742799155",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742799616"
},
"total": 461.25628523800015,
"count": 1,
"self": 0.44109518900017974,
"children": {
"run_training.setup": {
"total": 0.023164089999909265,
"count": 1,
"self": 0.023164089999909265
},
"TrainerController.start_learning": {
"total": 460.79202595900006,
"count": 1,
"self": 0.38154242399991745,
"children": {
"TrainerController._reset_env": {
"total": 3.0195098950000556,
"count": 1,
"self": 3.0195098950000556
},
"TrainerController.advance": {
"total": 457.294440358,
"count": 18192,
"self": 0.39114369399203497,
"children": {
"env_step": {
"total": 325.34838729699436,
"count": 18192,
"self": 247.01928812599772,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.10260360899747,
"count": 18192,
"self": 1.3473107130128028,
"children": {
"TorchPolicy.evaluate": {
"total": 76.75529289598467,
"count": 18192,
"self": 76.75529289598467
}
}
},
"workers": {
"total": 0.22649556199917242,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 459.14249642701475,
"count": 18192,
"is_parallel": true,
"self": 242.35488836502282,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004881453000052716,
"count": 1,
"is_parallel": true,
"self": 0.003383898000265617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014975549997870985,
"count": 10,
"is_parallel": true,
"self": 0.0014975549997870985
}
}
},
"UnityEnvironment.step": {
"total": 0.037552506999873,
"count": 1,
"is_parallel": true,
"self": 0.0007137589998365002,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000391624000030788,
"count": 1,
"is_parallel": true,
"self": 0.000391624000030788
},
"communicator.exchange": {
"total": 0.03369381500010604,
"count": 1,
"is_parallel": true,
"self": 0.03369381500010604
},
"steps_from_proto": {
"total": 0.002753308999899673,
"count": 1,
"is_parallel": true,
"self": 0.0004527789997155196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023005300001841533,
"count": 10,
"is_parallel": true,
"self": 0.0023005300001841533
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.78760806199193,
"count": 18191,
"is_parallel": true,
"self": 10.204785087033088,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.945587046964647,
"count": 18191,
"is_parallel": true,
"self": 5.945587046964647
},
"communicator.exchange": {
"total": 166.3036645289942,
"count": 18191,
"is_parallel": true,
"self": 166.3036645289942
},
"steps_from_proto": {
"total": 34.33357139899999,
"count": 18191,
"is_parallel": true,
"self": 6.1752727940051955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.158298604994798,
"count": 181910,
"is_parallel": true,
"self": 28.158298604994798
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 131.55490936701358,
"count": 18192,
"self": 0.4758765519993631,
"children": {
"process_trajectory": {
"total": 29.33746812501272,
"count": 18192,
"self": 28.769459675012513,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5680084500002067,
"count": 4,
"self": 0.5680084500002067
}
}
},
"_update_policy": {
"total": 101.7415646900015,
"count": 90,
"self": 41.77438468599871,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.967180004002785,
"count": 4587,
"self": 59.967180004002785
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0720000318542589e-06,
"count": 1,
"self": 1.0720000318542589e-06
},
"TrainerController._save_models": {
"total": 0.09653221000007761,
"count": 1,
"self": 0.0013086829999338079,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0952235270001438,
"count": 1,
"self": 0.0952235270001438
}
}
}
}
}
}
}