lodist's picture
First Push
eff7e69 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.8757917881011963,
"min": 2.8757917881011963,
"max": 2.8757917881011963,
"count": 1
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 29482.6171875,
"min": 29482.6171875,
"max": 29482.6171875,
"count": 1
},
"SnowballTarget.Step.mean": {
"value": 9952.0,
"min": 9952.0,
"max": 9952.0,
"count": 1
},
"SnowballTarget.Step.sum": {
"value": 9952.0,
"min": 9952.0,
"max": 9952.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.39630433917045593,
"min": 0.39630433917045593,
"max": 0.39630433917045593,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 76.88304138183594,
"min": 76.88304138183594,
"max": 76.88304138183594,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 1
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 8756.0,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07065940414067168,
"min": 0.07065940414067168,
"max": 0.07065940414067168,
"count": 1
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2826376165626867,
"min": 0.2826376165626867,
"max": 0.2826376165626867,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.11324942627620391,
"min": 0.11324942627620391,
"max": 0.11324942627620391,
"count": 1
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.45299770510481563,
"min": 0.45299770510481563,
"max": 0.45299770510481563,
"count": 1
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 0.000291882002706,
"min": 0.000291882002706,
"max": 0.000291882002706,
"count": 1
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.001167528010824,
"min": 0.001167528010824,
"max": 0.001167528010824,
"count": 1
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.19729400000000002,
"min": 0.19729400000000002,
"max": 0.19729400000000002,
"count": 1
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.7891760000000001,
"min": 0.7891760000000001,
"max": 0.7891760000000001,
"count": 1
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0048649706,
"min": 0.0048649706,
"max": 0.0048649706,
"count": 1
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0194598824,
"min": 0.0194598824,
"max": 0.0194598824,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 3.0454545454545454,
"min": 3.0454545454545454,
"max": 3.0454545454545454,
"count": 1
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 134.0,
"min": 134.0,
"max": 134.0,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 3.0454545454545454,
"min": 3.0454545454545454,
"max": 3.0454545454545454,
"count": 1
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 134.0,
"min": 134.0,
"max": 134.0,
"count": 1
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1734267101",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1734267158"
},
"total": 57.10475975999998,
"count": 1,
"self": 0.13939927499995974,
"children": {
"run_training.setup": {
"total": 0.10261077500001647,
"count": 1,
"self": 0.10261077500001647
},
"TrainerController.start_learning": {
"total": 56.86274971,
"count": 1,
"self": 0.20310606800205733,
"children": {
"TrainerController._reset_env": {
"total": 8.063556537999943,
"count": 1,
"self": 8.063556537999943
},
"TrainerController.advance": {
"total": 48.33727581899802,
"count": 1466,
"self": 0.036198854999611285,
"children": {
"env_step": {
"total": 48.30107696399841,
"count": 1466,
"self": 36.9792600340013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 11.2878025779969,
"count": 1466,
"self": 0.2183444459948305,
"children": {
"TorchPolicy.evaluate": {
"total": 11.069458132002069,
"count": 1466,
"self": 11.069458132002069
}
}
},
"workers": {
"total": 0.034014352000212966,
"count": 1465,
"self": 0.0,
"children": {
"worker_root": {
"total": 56.383046570997294,
"count": 1465,
"is_parallel": true,
"self": 31.013075718998834,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003822932999923978,
"count": 1,
"is_parallel": true,
"self": 0.0012727889999268882,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00255014399999709,
"count": 10,
"is_parallel": true,
"self": 0.00255014399999709
}
}
},
"UnityEnvironment.step": {
"total": 0.09860726499994144,
"count": 1,
"is_parallel": true,
"self": 0.0009232419998852492,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047340399999029614,
"count": 1,
"is_parallel": true,
"self": 0.00047340399999029614
},
"communicator.exchange": {
"total": 0.09379403700006606,
"count": 1,
"is_parallel": true,
"self": 0.09379403700006606
},
"steps_from_proto": {
"total": 0.003416581999999835,
"count": 1,
"is_parallel": true,
"self": 0.0005084360000182642,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029081459999815706,
"count": 10,
"is_parallel": true,
"self": 0.0029081459999815706
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 25.36997085199846,
"count": 1464,
"is_parallel": true,
"self": 1.2275205669983507,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.6354429189990469,
"count": 1464,
"is_parallel": true,
"self": 0.6354429189990469
},
"communicator.exchange": {
"total": 19.904830246998472,
"count": 1464,
"is_parallel": true,
"self": 19.904830246998472
},
"steps_from_proto": {
"total": 3.60217711900259,
"count": 1464,
"is_parallel": true,
"self": 0.7384784360132244,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.863698682989366,
"count": 14640,
"is_parallel": true,
"self": 2.863698682989366
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003375119999873277,
"count": 1,
"self": 0.0003375119999873277,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 47.89067564298773,
"count": 61017,
"is_parallel": true,
"self": 1.469437408002932,
"children": {
"process_trajectory": {
"total": 25.919111242984854,
"count": 61017,
"is_parallel": true,
"self": 25.919111242984854
},
"_update_policy": {
"total": 20.502126991999944,
"count": 7,
"is_parallel": true,
"self": 6.512655667000217,
"children": {
"TorchPPOOptimizer.update": {
"total": 13.989471324999727,
"count": 354,
"is_parallel": true,
"self": 13.989471324999727
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2584737729999915,
"count": 1,
"self": 0.0021124790000612848,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25636129399993024,
"count": 1,
"self": 0.25636129399993024
}
}
}
}
}
}
}