papepipopu's picture
Yo
86227f1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8784732222557068,
"min": 0.8784732222557068,
"max": 2.8655760288238525,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8426.3154296875,
"min": 8426.3154296875,
"max": 29850.705078125,
"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": 12.933926582336426,
"min": 0.3649980127811432,
"max": 12.933926582336426,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1306.3265380859375,
"min": 35.404808044433594,
"max": 1306.3265380859375,
"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.Environment.CumulativeReward.mean": {
"value": 25.884615384615383,
"min": 3.590909090909091,
"max": 25.884615384615383,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1346.0,
"min": 158.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.884615384615383,
"min": 3.590909090909091,
"max": 25.884615384615383,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1346.0,
"min": 158.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06396107849671835,
"min": 0.06371097970872606,
"max": 0.07991538735359963,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2558443139868734,
"min": 0.25484391883490426,
"max": 0.3995769367679981,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16029272075085077,
"min": 0.10141668255057404,
"max": 0.2176857413906677,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6411708830034031,
"min": 0.40566673020229616,
"max": 1.0501637137403674,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.950097350000008e-06,
"min": 7.950097350000008e-06,
"max": 0.00029175000274999995,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.180038940000003e-05,
"min": 3.180038940000003e-05,
"max": 0.0013845000385,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10265,
"min": 0.10265,
"max": 0.19725000000000004,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4106,
"min": 0.4106,
"max": 0.9615,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014223500000000013,
"min": 0.00014223500000000013,
"max": 0.004862775,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005689400000000005,
"min": 0.0005689400000000005,
"max": 0.023078849999999998,
"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": "1691839168",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691839614"
},
"total": 445.794754043,
"count": 1,
"self": 0.6936936380000134,
"children": {
"run_training.setup": {
"total": 0.04388441600008264,
"count": 1,
"self": 0.04388441600008264
},
"TrainerController.start_learning": {
"total": 445.0571759889999,
"count": 1,
"self": 0.5715720489981777,
"children": {
"TrainerController._reset_env": {
"total": 4.151905508000027,
"count": 1,
"self": 4.151905508000027
},
"TrainerController.advance": {
"total": 440.0921997040016,
"count": 18236,
"self": 0.2778416949934126,
"children": {
"env_step": {
"total": 439.8143580090082,
"count": 18236,
"self": 301.08223405002093,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.40250713598903,
"count": 18236,
"self": 1.629585276994817,
"children": {
"TorchPolicy.evaluate": {
"total": 136.7729218589942,
"count": 18236,
"self": 136.7729218589942
}
}
},
"workers": {
"total": 0.3296168229982186,
"count": 18236,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.27781700599735,
"count": 18236,
"is_parallel": true,
"self": 197.66064962199778,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006420464000029824,
"count": 1,
"is_parallel": true,
"self": 0.004872999999861349,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015474640001684747,
"count": 10,
"is_parallel": true,
"self": 0.0015474640001684747
}
}
},
"UnityEnvironment.step": {
"total": 0.039725858999986485,
"count": 1,
"is_parallel": true,
"self": 0.0006951179999532542,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035182400006306125,
"count": 1,
"is_parallel": true,
"self": 0.00035182400006306125
},
"communicator.exchange": {
"total": 0.03612953100002869,
"count": 1,
"is_parallel": true,
"self": 0.03612953100002869
},
"steps_from_proto": {
"total": 0.002549385999941478,
"count": 1,
"is_parallel": true,
"self": 0.0004556130002129066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020937729997285714,
"count": 10,
"is_parallel": true,
"self": 0.0020937729997285714
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.61716738399957,
"count": 18235,
"is_parallel": true,
"self": 10.271496617979437,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.1764364840082635,
"count": 18235,
"is_parallel": true,
"self": 5.1764364840082635
},
"communicator.exchange": {
"total": 194.76915340799792,
"count": 18235,
"is_parallel": true,
"self": 194.76915340799792
},
"steps_from_proto": {
"total": 35.40008087401395,
"count": 18235,
"is_parallel": true,
"self": 6.421729068018863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.97835180599509,
"count": 182350,
"is_parallel": true,
"self": 28.97835180599509
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00026739700001598976,
"count": 1,
"self": 0.00026739700001598976,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.5905905019897,
"count": 224282,
"is_parallel": true,
"self": 4.982553473002326,
"children": {
"process_trajectory": {
"total": 148.94416251298787,
"count": 224282,
"is_parallel": true,
"self": 146.9714476389879,
"children": {
"RLTrainer._checkpoint": {
"total": 1.972714873999962,
"count": 4,
"is_parallel": true,
"self": 1.972714873999962
}
}
},
"_update_policy": {
"total": 284.6638745159995,
"count": 90,
"is_parallel": true,
"self": 93.3395812799996,
"children": {
"TorchPPOOptimizer.update": {
"total": 191.3242932359999,
"count": 4590,
"is_parallel": true,
"self": 191.3242932359999
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.24123133100010818,
"count": 1,
"self": 0.001165518000107113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24006581300000107,
"count": 1,
"self": 0.24006581300000107
}
}
}
}
}
}
}