Martox's picture
First Push
19080b1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6477712392807007,
"min": 0.6477712392807007,
"max": 2.837028980255127,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6156.41796875,
"min": 6156.41796875,
"max": 28960.392578125,
"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": 13.166440963745117,
"min": 0.3638096749782562,
"max": 13.166440963745117,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2567.4560546875,
"min": 70.5790786743164,
"max": 2678.223388671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06990579404016756,
"min": 0.06351837165945887,
"max": 0.07548053766139692,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27962317616067023,
"min": 0.2745045790740964,
"max": 0.367985946856018,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19138045053856043,
"min": 0.1129639441770611,
"max": 0.287679289485894,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7655218021542417,
"min": 0.4518557767082444,
"max": 1.4243174271256316,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.113636363636363,
"min": 3.5454545454545454,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1149.0,
"min": 156.0,
"max": 1428.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.113636363636363,
"min": 3.5454545454545454,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1149.0,
"min": 156.0,
"max": 1428.0,
"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": "1768434406",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1768434830"
},
"total": 423.51047670699995,
"count": 1,
"self": 0.4343626319998748,
"children": {
"run_training.setup": {
"total": 0.025065984000093522,
"count": 1,
"self": 0.025065984000093522
},
"TrainerController.start_learning": {
"total": 423.051048091,
"count": 1,
"self": 0.3193403710019993,
"children": {
"TrainerController._reset_env": {
"total": 2.7051174389998778,
"count": 1,
"self": 2.7051174389998778
},
"TrainerController.advance": {
"total": 419.9511707259978,
"count": 18192,
"self": 0.330826188982428,
"children": {
"env_step": {
"total": 302.57406554900626,
"count": 18192,
"self": 236.71588298298366,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.66189224301934,
"count": 18192,
"self": 1.1958809690461294,
"children": {
"TorchPolicy.evaluate": {
"total": 64.46601127397321,
"count": 18192,
"self": 64.46601127397321
}
}
},
"workers": {
"total": 0.19629032300326799,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 421.3666553270234,
"count": 18192,
"is_parallel": true,
"self": 213.25018641602628,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004943749000176467,
"count": 1,
"is_parallel": true,
"self": 0.003532968000627079,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001410780999549388,
"count": 10,
"is_parallel": true,
"self": 0.001410780999549388
}
}
},
"UnityEnvironment.step": {
"total": 0.03481553799997528,
"count": 1,
"is_parallel": true,
"self": 0.00070699799994145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004335660000833741,
"count": 1,
"is_parallel": true,
"self": 0.0004335660000833741
},
"communicator.exchange": {
"total": 0.03171789499992883,
"count": 1,
"is_parallel": true,
"self": 0.03171789499992883
},
"steps_from_proto": {
"total": 0.001957079000021622,
"count": 1,
"is_parallel": true,
"self": 0.00039253300019481685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015645459998268052,
"count": 10,
"is_parallel": true,
"self": 0.0015645459998268052
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 208.11646891099713,
"count": 18191,
"is_parallel": true,
"self": 10.096566336017077,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.259939125007122,
"count": 18191,
"is_parallel": true,
"self": 5.259939125007122
},
"communicator.exchange": {
"total": 157.84382949997598,
"count": 18191,
"is_parallel": true,
"self": 157.84382949997598
},
"steps_from_proto": {
"total": 34.91613394999695,
"count": 18191,
"is_parallel": true,
"self": 6.402038578987003,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.514095371009944,
"count": 181910,
"is_parallel": true,
"self": 28.514095371009944
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 117.04627898800913,
"count": 18192,
"self": 0.38535609400196336,
"children": {
"process_trajectory": {
"total": 25.51765412900795,
"count": 18192,
"self": 25.078973732008308,
"children": {
"RLTrainer._checkpoint": {
"total": 0.43868039699964356,
"count": 4,
"self": 0.43868039699964356
}
}
},
"_update_policy": {
"total": 91.14326876499922,
"count": 90,
"self": 38.33892334201528,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.80434542298394,
"count": 4587,
"self": 52.80434542298394
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.900001375877764e-07,
"count": 1,
"self": 8.900001375877764e-07
},
"TrainerController._save_models": {
"total": 0.07541866500014294,
"count": 1,
"self": 0.0009403640001437452,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07447830099999919,
"count": 1,
"self": 0.07447830099999919
}
}
}
}
}
}
}