{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9132306575775146,
"min": 0.9029188752174377,
"max": 2.8719892501831055,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8739.6171875,
"min": 8739.6171875,
"max": 29443.634765625,
"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": 12.79339599609375,
"min": 0.3225421607494354,
"max": 12.79339599609375,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2494.712158203125,
"min": 62.573177337646484,
"max": 2609.026611328125,
"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": 0.06670823510748781,
"min": 0.0645620163294998,
"max": 0.07008971572327473,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26683294042995126,
"min": 0.2625689993462455,
"max": 0.34324241380547355,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1872563904114798,
"min": 0.1356035951438232,
"max": 0.274434738226381,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7490255616459192,
"min": 0.5424143805752928,
"max": 1.3627054676705714,
"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": 25.136363636363637,
"min": 3.6818181818181817,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 162.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.6818181818181817,
"max": 25.568181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 162.0,
"max": 1395.0,
"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": "1732947165",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/meipodai/miniconda3/envs/RL_hugging_face/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1",
"numpy_version": "1.23.5",
"end_time_seconds": "1732947471"
},
"total": 306.040100592,
"count": 1,
"self": 0.21914932800001452,
"children": {
"run_training.setup": {
"total": 0.03031264100000186,
"count": 1,
"self": 0.03031264100000186
},
"TrainerController.start_learning": {
"total": 305.79063862299995,
"count": 1,
"self": 0.4510733480007616,
"children": {
"TrainerController._reset_env": {
"total": 1.5613501409999984,
"count": 1,
"self": 1.5613501409999984
},
"TrainerController.advance": {
"total": 303.73410471899916,
"count": 18203,
"self": 0.19453240599807486,
"children": {
"env_step": {
"total": 303.5395723130011,
"count": 18203,
"self": 239.87535303400531,
"children": {
"SubprocessEnvManager._take_step": {
"total": 63.45231134599565,
"count": 18203,
"self": 0.8779951619952655,
"children": {
"TorchPolicy.evaluate": {
"total": 62.57431618400039,
"count": 18203,
"self": 62.57431618400039
}
}
},
"workers": {
"total": 0.211907933000127,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 305.1375331239977,
"count": 18203,
"is_parallel": true,
"self": 126.85814226300155,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018524190000022145,
"count": 1,
"is_parallel": true,
"self": 0.0008989169999935598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009535020000086547,
"count": 10,
"is_parallel": true,
"self": 0.0009535020000086547
}
}
},
"UnityEnvironment.step": {
"total": 0.019822671000000014,
"count": 1,
"is_parallel": true,
"self": 0.0002444870000033461,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002032089999985942,
"count": 1,
"is_parallel": true,
"self": 0.0002032089999985942
},
"communicator.exchange": {
"total": 0.018582609999995725,
"count": 1,
"is_parallel": true,
"self": 0.018582609999995725
},
"steps_from_proto": {
"total": 0.0007923650000023486,
"count": 1,
"is_parallel": true,
"self": 0.0001850640000071735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006073009999951751,
"count": 10,
"is_parallel": true,
"self": 0.0006073009999951751
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 178.27939086099613,
"count": 18202,
"is_parallel": true,
"self": 4.127399165998071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.008534034999947,
"count": 18202,
"is_parallel": true,
"self": 3.008534034999947
},
"communicator.exchange": {
"total": 157.972730974999,
"count": 18202,
"is_parallel": true,
"self": 157.972730974999
},
"steps_from_proto": {
"total": 13.170726684999131,
"count": 18202,
"is_parallel": true,
"self": 3.1360408949954746,
"children": {
"_process_rank_one_or_two_observation": {
"total": 10.034685790003657,
"count": 182020,
"is_parallel": true,
"self": 10.034685790003657
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016772100002526713,
"count": 1,
"self": 0.00016772100002526713,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 302.0814062969958,
"count": 306069,
"is_parallel": true,
"self": 5.290993345996867,
"children": {
"process_trajectory": {
"total": 168.24575259499892,
"count": 306069,
"is_parallel": true,
"self": 167.861200308999,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3845522859999164,
"count": 4,
"is_parallel": true,
"self": 0.3845522859999164
}
}
},
"_update_policy": {
"total": 128.544660356,
"count": 90,
"is_parallel": true,
"self": 23.600778065001435,
"children": {
"TorchPPOOptimizer.update": {
"total": 104.94388229099857,
"count": 4587,
"is_parallel": true,
"self": 104.94388229099857
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.04394269400000894,
"count": 1,
"self": 0.0008689420000109749,
"children": {
"RLTrainer._checkpoint": {
"total": 0.04307375199999797,
"count": 1,
"self": 0.04307375199999797
}
}
}
}
}
}
}