kjmann's picture
commit from hf course
a650dba
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7858220934867859,
"min": 0.7858220934867859,
"max": 2.8676912784576416,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7503.029296875,
"min": 7503.029296875,
"max": 29368.025390625,
"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": 2.555189847946167,
"min": 0.22978362441062927,
"max": 2.5841102600097656,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 498.26202392578125,
"min": 44.57802200317383,
"max": 525.5888671875,
"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": 0.06644664385313781,
"min": 0.0630658492865954,
"max": 0.07416749561625516,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26578657541255124,
"min": 0.2570122290906547,
"max": 0.36690108714552194,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.14434334237639812,
"min": 0.06270317510672042,
"max": 0.15523014962673187,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5773733695055925,
"min": 0.2508127004268817,
"max": 0.7535666620322301,
"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": 25.227272727272727,
"min": 3.272727272727273,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1110.0,
"min": 144.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.227272727272727,
"min": 3.272727272727273,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1110.0,
"min": 144.0,
"max": 1385.0,
"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": "1674806001",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674806420"
},
"total": 419.697284805,
"count": 1,
"self": 0.3902056399998628,
"children": {
"run_training.setup": {
"total": 0.10163934600006996,
"count": 1,
"self": 0.10163934600006996
},
"TrainerController.start_learning": {
"total": 419.20543981900005,
"count": 1,
"self": 0.5404084540052736,
"children": {
"TrainerController._reset_env": {
"total": 9.005007615999943,
"count": 1,
"self": 9.005007615999943
},
"TrainerController.advance": {
"total": 409.5427180009949,
"count": 18202,
"self": 0.2790402129935501,
"children": {
"env_step": {
"total": 409.26367778800136,
"count": 18202,
"self": 268.129738257011,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.8641064189984,
"count": 18202,
"self": 1.3755540259913914,
"children": {
"TorchPolicy.evaluate": {
"total": 139.488552393007,
"count": 18202,
"self": 30.334688636006035,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.15386375700098,
"count": 18202,
"self": 109.15386375700098
}
}
}
}
},
"workers": {
"total": 0.26983311199194304,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 418.0554296910001,
"count": 18202,
"is_parallel": true,
"self": 201.19592211899635,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006118235000030836,
"count": 1,
"is_parallel": true,
"self": 0.0036497479998160998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024684870002147363,
"count": 10,
"is_parallel": true,
"self": 0.0024684870002147363
}
}
},
"UnityEnvironment.step": {
"total": 0.04140579899990371,
"count": 1,
"is_parallel": true,
"self": 0.0005394409998871197,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042871100004049367,
"count": 1,
"is_parallel": true,
"self": 0.00042871100004049367
},
"communicator.exchange": {
"total": 0.03858376599998792,
"count": 1,
"is_parallel": true,
"self": 0.03858376599998792
},
"steps_from_proto": {
"total": 0.0018538809999881778,
"count": 1,
"is_parallel": true,
"self": 0.0004698349997624973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013840460002256805,
"count": 10,
"is_parallel": true,
"self": 0.0013840460002256805
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.85950757200374,
"count": 18201,
"is_parallel": true,
"self": 8.207319869000003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.747853359000715,
"count": 18201,
"is_parallel": true,
"self": 4.747853359000715
},
"communicator.exchange": {
"total": 175.12724331200684,
"count": 18201,
"is_parallel": true,
"self": 175.12724331200684
},
"steps_from_proto": {
"total": 28.77709103199618,
"count": 18201,
"is_parallel": true,
"self": 6.171889480971458,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.60520155102472,
"count": 182010,
"is_parallel": true,
"self": 22.60520155102472
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.037399992284918e-05,
"count": 1,
"self": 4.037399992284918e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 406.69753947197034,
"count": 337216,
"is_parallel": true,
"self": 9.351684663983406,
"children": {
"process_trajectory": {
"total": 232.96581782498652,
"count": 337216,
"is_parallel": true,
"self": 232.27823896598647,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6875788590000411,
"count": 4,
"is_parallel": true,
"self": 0.6875788590000411
}
}
},
"_update_policy": {
"total": 164.38003698300042,
"count": 90,
"is_parallel": true,
"self": 42.090019034998136,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.29001794800229,
"count": 4587,
"is_parallel": true,
"self": 122.29001794800229
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1172653739999987,
"count": 1,
"self": 0.0008592689999886716,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11640610500001003,
"count": 1,
"self": 0.11640610500001003
}
}
}
}
}
}
}