fancyerii's picture
First Push
108e45a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8928395509719849,
"min": 0.8928395509719849,
"max": 2.8338327407836914,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8485.546875,
"min": 8485.546875,
"max": 28927.765625,
"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": 12.877572059631348,
"min": 0.3878212869167328,
"max": 12.877572059631348,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.12646484375,
"min": 75.2373275756836,
"max": 2616.68212890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06720923803660815,
"min": 0.05869276300854479,
"max": 0.07328331564934285,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2688369521464326,
"min": 0.24161597500999193,
"max": 0.3595265390479243,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2129101403349755,
"min": 0.1421382353086408,
"max": 0.264626889369067,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.851640561339902,
"min": 0.5685529412345632,
"max": 1.323134446845335,
"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": 25.363636363636363,
"min": 3.6363636363636362,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 160.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.6363636363636362,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 160.0,
"max": 1388.0,
"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": "1751092949",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751093397"
},
"total": 448.213865468,
"count": 1,
"self": 0.438268389999962,
"children": {
"run_training.setup": {
"total": 0.022803533000001153,
"count": 1,
"self": 0.022803533000001153
},
"TrainerController.start_learning": {
"total": 447.75279354500003,
"count": 1,
"self": 0.42066039501219166,
"children": {
"TrainerController._reset_env": {
"total": 3.2284658629999967,
"count": 1,
"self": 3.2284658629999967
},
"TrainerController.advance": {
"total": 443.9996629999879,
"count": 18192,
"self": 0.4374360479968118,
"children": {
"env_step": {
"total": 323.36978475198885,
"count": 18192,
"self": 249.5397658279968,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.59031973599235,
"count": 18192,
"self": 1.3722387979991026,
"children": {
"TorchPolicy.evaluate": {
"total": 72.21808093799325,
"count": 18192,
"self": 72.21808093799325
}
}
},
"workers": {
"total": 0.23969918799969037,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.18015062200107,
"count": 18192,
"is_parallel": true,
"self": 227.47932643499166,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053035300001056385,
"count": 1,
"is_parallel": true,
"self": 0.0037803280000616724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015232020000439661,
"count": 10,
"is_parallel": true,
"self": 0.0015232020000439661
}
}
},
"UnityEnvironment.step": {
"total": 0.03741738099995473,
"count": 1,
"is_parallel": true,
"self": 0.0006394689999069669,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040900800001963944,
"count": 1,
"is_parallel": true,
"self": 0.00040900800001963944
},
"communicator.exchange": {
"total": 0.03436244700003499,
"count": 1,
"is_parallel": true,
"self": 0.03436244700003499
},
"steps_from_proto": {
"total": 0.0020064569999931336,
"count": 1,
"is_parallel": true,
"self": 0.0004128360000095199,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015936209999836137,
"count": 10,
"is_parallel": true,
"self": 0.0015936209999836137
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.7008241870094,
"count": 18191,
"is_parallel": true,
"self": 10.269199624008024,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.776109423995081,
"count": 18191,
"is_parallel": true,
"self": 5.776109423995081
},
"communicator.exchange": {
"total": 168.4502991810076,
"count": 18191,
"is_parallel": true,
"self": 168.4502991810076
},
"steps_from_proto": {
"total": 34.20521595799869,
"count": 18191,
"is_parallel": true,
"self": 6.139886501995306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.065329456003383,
"count": 181910,
"is_parallel": true,
"self": 28.065329456003383
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.19244220000223,
"count": 18192,
"self": 0.5238314870136946,
"children": {
"process_trajectory": {
"total": 27.15825713098843,
"count": 18192,
"self": 26.74636872298811,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41188840800032267,
"count": 4,
"self": 0.41188840800032267
}
}
},
"_update_policy": {
"total": 92.5103535820001,
"count": 90,
"self": 38.00566166599708,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.504691916003026,
"count": 4587,
"self": 54.504691916003026
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7329998627246823e-06,
"count": 1,
"self": 1.7329998627246823e-06
},
"TrainerController._save_models": {
"total": 0.10400255400008973,
"count": 1,
"self": 0.0009037390000230516,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10309881500006668,
"count": 1,
"self": 0.10309881500006668
}
}
}
}
}
}
}