jjlira's picture
my first try
a72f1d6
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8983109593391418,
"min": 0.860023558139801,
"max": 2.879204034805298,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8577.0732421875,
"min": 8567.8076171875,
"max": 29612.61328125,
"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": 12.988750457763672,
"min": 0.4335065484046936,
"max": 12.988750457763672,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2532.806396484375,
"min": 84.10027313232422,
"max": 2648.203125,
"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": 0.06834071454838576,
"min": 0.06277492564860913,
"max": 0.07900690164387925,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27336285819354306,
"min": 0.2643339290792264,
"max": 0.36165249300892377,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2178538471606432,
"min": 0.12306866488606649,
"max": 0.28291880768888134,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8714153886425728,
"min": 0.49227465954426597,
"max": 1.4145940384444067,
"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": 25.363636363636363,
"min": 3.3863636363636362,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 149.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.3863636363636362,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 149.0,
"max": 1410.0,
"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": "1679115539",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679115994"
},
"total": 454.64369784199994,
"count": 1,
"self": 0.42768144699971344,
"children": {
"run_training.setup": {
"total": 0.16674632000012934,
"count": 1,
"self": 0.16674632000012934
},
"TrainerController.start_learning": {
"total": 454.0492700750001,
"count": 1,
"self": 0.5382369789858785,
"children": {
"TrainerController._reset_env": {
"total": 6.621134710999968,
"count": 1,
"self": 6.621134710999968
},
"TrainerController.advance": {
"total": 446.7601687880142,
"count": 18201,
"self": 0.28382491503680285,
"children": {
"env_step": {
"total": 446.4763438729774,
"count": 18201,
"self": 322.45485917198516,
"children": {
"SubprocessEnvManager._take_step": {
"total": 123.75614003298665,
"count": 18201,
"self": 2.0821260439697653,
"children": {
"TorchPolicy.evaluate": {
"total": 121.67401398901688,
"count": 18201,
"self": 121.67401398901688
}
}
},
"workers": {
"total": 0.2653446680055822,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.7017580340064,
"count": 18201,
"is_parallel": true,
"self": 215.55493400500723,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003044024000018908,
"count": 1,
"is_parallel": true,
"self": 0.0008590990000811871,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021849249999377207,
"count": 10,
"is_parallel": true,
"self": 0.0021849249999377207
}
}
},
"UnityEnvironment.step": {
"total": 0.04332894200001647,
"count": 1,
"is_parallel": true,
"self": 0.0005691790001947084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004833139998936531,
"count": 1,
"is_parallel": true,
"self": 0.0004833139998936531
},
"communicator.exchange": {
"total": 0.04023863599991273,
"count": 1,
"is_parallel": true,
"self": 0.04023863599991273
},
"steps_from_proto": {
"total": 0.002037813000015376,
"count": 1,
"is_parallel": true,
"self": 0.00036220500032868586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016756079996866902,
"count": 10,
"is_parallel": true,
"self": 0.0016756079996866902
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.14682402899916,
"count": 18200,
"is_parallel": true,
"self": 9.318424597992816,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.099630626008775,
"count": 18200,
"is_parallel": true,
"self": 5.099630626008775
},
"communicator.exchange": {
"total": 192.54294271100298,
"count": 18200,
"is_parallel": true,
"self": 192.54294271100298
},
"steps_from_proto": {
"total": 30.185826093994592,
"count": 18200,
"is_parallel": true,
"self": 6.033246779957153,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.15257931403744,
"count": 182000,
"is_parallel": true,
"self": 24.15257931403744
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.37009999941074e-05,
"count": 1,
"self": 8.37009999941074e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.6004052609376,
"count": 395566,
"is_parallel": true,
"self": 9.313614404891496,
"children": {
"process_trajectory": {
"total": 245.67634075004503,
"count": 395566,
"is_parallel": true,
"self": 244.47703368304497,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1993070670000634,
"count": 4,
"is_parallel": true,
"self": 1.1993070670000634
}
}
},
"_update_policy": {
"total": 188.61045010600105,
"count": 90,
"is_parallel": true,
"self": 69.52881735900655,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.0816327469945,
"count": 4584,
"is_parallel": true,
"self": 119.0816327469945
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12964589600005638,
"count": 1,
"self": 0.0008824650001315604,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12876343099992482,
"count": 1,
"self": 0.12876343099992482
}
}
}
}
}
}
}