Raiden-1001's picture
First Push
555497e
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9476500749588013,
"min": 0.9476500749588013,
"max": 2.8732717037200928,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9048.1630859375,
"min": 9048.1630859375,
"max": 29456.78125,
"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": 12.94500732421875,
"min": 0.39464983344078064,
"max": 12.94500732421875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.2763671875,
"min": 76.56206512451172,
"max": 2636.840576171875,
"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": 0.07081659866390491,
"min": 0.06144252755435517,
"max": 0.08051453464434542,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28326639465561965,
"min": 0.24577011021742068,
"max": 0.36009903478564004,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2031686904968,
"min": 0.12608512096773541,
"max": 0.2872549860500822,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8126747619872,
"min": 0.5043404838709417,
"max": 1.436274930250411,
"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": 25.545454545454547,
"min": 3.5454545454545454,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 156.0,
"max": 1430.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.5454545454545454,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 156.0,
"max": 1430.0,
"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": "1679203676",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679204140"
},
"total": 463.96635741299986,
"count": 1,
"self": 0.43664715199986404,
"children": {
"run_training.setup": {
"total": 0.11120161899998493,
"count": 1,
"self": 0.11120161899998493
},
"TrainerController.start_learning": {
"total": 463.418508642,
"count": 1,
"self": 0.5140147320175856,
"children": {
"TrainerController._reset_env": {
"total": 9.565871488000084,
"count": 1,
"self": 9.565871488000084
},
"TrainerController.advance": {
"total": 453.2042840359827,
"count": 18202,
"self": 0.2755845929845009,
"children": {
"env_step": {
"total": 452.9286994429982,
"count": 18202,
"self": 327.14647033899496,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.50947520301258,
"count": 18202,
"self": 2.0525710489996527,
"children": {
"TorchPolicy.evaluate": {
"total": 123.45690415401293,
"count": 18202,
"self": 123.45690415401293
}
}
},
"workers": {
"total": 0.272753900990665,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.07695747499497,
"count": 18202,
"is_parallel": true,
"self": 221.8096633460167,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005527125999947202,
"count": 1,
"is_parallel": true,
"self": 0.004083163999894168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001443962000053034,
"count": 10,
"is_parallel": true,
"self": 0.001443962000053034
}
}
},
"UnityEnvironment.step": {
"total": 0.11156489899997268,
"count": 1,
"is_parallel": true,
"self": 0.0006265019999318611,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035497199996825657,
"count": 1,
"is_parallel": true,
"self": 0.00035497199996825657
},
"communicator.exchange": {
"total": 0.10831526399999802,
"count": 1,
"is_parallel": true,
"self": 0.10831526399999802
},
"steps_from_proto": {
"total": 0.0022681610000745422,
"count": 1,
"is_parallel": true,
"self": 0.00044166099996800767,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018265000001065346,
"count": 10,
"is_parallel": true,
"self": 0.0018265000001065346
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.26729412897828,
"count": 18201,
"is_parallel": true,
"self": 9.451459464973027,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.080972940996389,
"count": 18201,
"is_parallel": true,
"self": 5.080972940996389
},
"communicator.exchange": {
"total": 194.6139553609927,
"count": 18201,
"is_parallel": true,
"self": 194.6139553609927
},
"steps_from_proto": {
"total": 31.12090636201617,
"count": 18201,
"is_parallel": true,
"self": 6.098008506011638,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.022897856004533,
"count": 182010,
"is_parallel": true,
"self": 25.022897856004533
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011723399984475691,
"count": 1,
"self": 0.00011723399984475691,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 449.8715284410872,
"count": 410291,
"is_parallel": true,
"self": 9.76502795408851,
"children": {
"process_trajectory": {
"total": 247.62458173299842,
"count": 410291,
"is_parallel": true,
"self": 246.69788706399868,
"children": {
"RLTrainer._checkpoint": {
"total": 0.926694668999744,
"count": 4,
"is_parallel": true,
"self": 0.926694668999744
}
}
},
"_update_policy": {
"total": 192.48191875400028,
"count": 90,
"is_parallel": true,
"self": 74.08074665800643,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.40117209599384,
"count": 4587,
"is_parallel": true,
"self": 118.40117209599384
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1342211519997818,
"count": 1,
"self": 0.0009537849998650927,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1332673669999167,
"count": 1,
"self": 0.1332673669999167
}
}
}
}
}
}
}