shahmaty's picture
First Push
90afaac verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.311468243598938,
"min": 1.2958147525787354,
"max": 2.890296459197998,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12579.603515625,
"min": 12315.4228515625,
"max": 29721.23046875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 10.708931922912598,
"min": 0.10068845003843307,
"max": 10.708931922912598,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2195.3310546875,
"min": 19.533559799194336,
"max": 2195.3310546875,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.09090909090909,
"min": 2.7045454545454546,
"max": 22.155555555555555,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1215.0,
"min": 119.0,
"max": 1215.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.09090909090909,
"min": 2.7045454545454546,
"max": 22.155555555555555,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1215.0,
"min": 119.0,
"max": 1215.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.01998938781519731,
"min": 0.015459890911976496,
"max": 0.03154410559218377,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.01998938781519731,
"min": 0.015459890911976496,
"max": 0.03154410559218377,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22423367003599803,
"min": 0.09153692275285721,
"max": 0.3323996235926946,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.22423367003599803,
"min": 0.09153692275285721,
"max": 0.3323996235926946,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.2176982607999905e-06,
"min": 5.2176982607999905e-06,
"max": 0.00029345280218239997,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10173919999999997,
"min": 0.10173919999999997,
"max": 0.19781759999999993,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.678607999999983e-05,
"min": 9.678607999999983e-05,
"max": 0.004891098240000001,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1745525286",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745526261"
},
"total": 974.8251190530002,
"count": 1,
"self": 0.5348691440003677,
"children": {
"run_training.setup": {
"total": 0.022635892999915086,
"count": 1,
"self": 0.022635892999915086
},
"TrainerController.start_learning": {
"total": 974.2676140159999,
"count": 1,
"self": 0.9622756729977482,
"children": {
"TrainerController._reset_env": {
"total": 3.401621080000041,
"count": 1,
"self": 3.401621080000041
},
"TrainerController.advance": {
"total": 969.8259619400026,
"count": 45464,
"self": 1.000259436992792,
"children": {
"env_step": {
"total": 775.3539987120075,
"count": 45464,
"self": 597.064191221029,
"children": {
"SubprocessEnvManager._take_step": {
"total": 177.70953752199648,
"count": 45464,
"self": 3.326485988991408,
"children": {
"TorchPolicy.evaluate": {
"total": 174.38305153300507,
"count": 45464,
"self": 174.38305153300507
}
}
},
"workers": {
"total": 0.5802699689820656,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 970.8714874070454,
"count": 45464,
"is_parallel": true,
"self": 446.8568297110287,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011373681999884866,
"count": 1,
"is_parallel": true,
"self": 0.009813988000587415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015596939992974512,
"count": 10,
"is_parallel": true,
"self": 0.0015596939992974512
}
}
},
"UnityEnvironment.step": {
"total": 0.03599408000013682,
"count": 1,
"is_parallel": true,
"self": 0.0006283540001277288,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037350100001276587,
"count": 1,
"is_parallel": true,
"self": 0.00037350100001276587
},
"communicator.exchange": {
"total": 0.03299435300004916,
"count": 1,
"is_parallel": true,
"self": 0.03299435300004916
},
"steps_from_proto": {
"total": 0.001997871999947165,
"count": 1,
"is_parallel": true,
"self": 0.0004124760000649985,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015853959998821665,
"count": 10,
"is_parallel": true,
"self": 0.0015853959998821665
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 524.0146576960167,
"count": 45463,
"is_parallel": true,
"self": 24.46604668497457,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.939138985007958,
"count": 45463,
"is_parallel": true,
"self": 13.939138985007958
},
"communicator.exchange": {
"total": 403.7978131520106,
"count": 45463,
"is_parallel": true,
"self": 403.7978131520106
},
"steps_from_proto": {
"total": 81.81165887402358,
"count": 45463,
"is_parallel": true,
"self": 14.93427050588889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.87738836813469,
"count": 454630,
"is_parallel": true,
"self": 66.87738836813469
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 193.47170379100226,
"count": 45464,
"self": 1.174378638993403,
"children": {
"process_trajectory": {
"total": 70.47802814100942,
"count": 45464,
"self": 70.33443623300946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14359190799996213,
"count": 1,
"self": 0.14359190799996213
}
}
},
"_update_policy": {
"total": 121.81929701099943,
"count": 47,
"self": 93.84546603599529,
"children": {
"TorchPPOOptimizer.update": {
"total": 27.973830975004148,
"count": 1410,
"self": 27.973830975004148
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.699998943484388e-07,
"count": 1,
"self": 8.699998943484388e-07
},
"TrainerController._save_models": {
"total": 0.07775445299967032,
"count": 1,
"self": 0.0005478049993143941,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07720664800035593,
"count": 1,
"self": 0.07720664800035593
}
}
}
}
}
}
}