Vishath's picture
First Push
6f30438 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7947547435760498,
"min": 0.7770571708679199,
"max": 2.8860361576080322,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 4615.935546875,
"min": 3419.051513671875,
"max": 16762.09765625,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 4912.0,
"max": 499912.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 4912.0,
"max": 499912.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.608094215393066,
"min": 0.017430484294891357,
"max": 14.64759635925293,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 715.796630859375,
"min": 0.8366632461547852,
"max": 773.0584106445312,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.82608695652174,
"min": 2.727272727272727,
"max": 29.363636363636363,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 640.0,
"min": 60.0,
"max": 871.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.82608695652174,
"min": 2.727272727272727,
"max": 29.363636363636363,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 640.0,
"min": 60.0,
"max": 871.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05360421963611289,
"min": 0.04283988371368169,
"max": 0.0587533274648355,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.05360421963611289,
"min": 0.04283988371368169,
"max": 0.10815275633324156,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.13718131430008831,
"min": 0.09530569371931694,
"max": 0.3227748593863319,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.13718131430008831,
"min": 0.09530569371931694,
"max": 0.5621554663952659,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6800994400000147e-06,
"min": 1.6800994400000147e-06,
"max": 0.00029736000088000005,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.6800994400000147e-06,
"min": 1.6800994400000147e-06,
"max": 0.0005551200149599998,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10056,
"min": 0.10056,
"max": 0.19912,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10056,
"min": 0.10056,
"max": 0.38504000000000005,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.674400000000014e-05,
"min": 2.674400000000014e-05,
"max": 0.002973687999999999,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 2.674400000000014e-05,
"min": 2.674400000000014e-05,
"max": 0.005552695999999999,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1765869664",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/envs/mlagents_env/bin/mlagents-learn /content/ml-agents/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": "1765871080"
},
"total": 1415.8811883150001,
"count": 1,
"self": 0.4835859410000012,
"children": {
"run_training.setup": {
"total": 0.027849017999983516,
"count": 1,
"self": 0.027849017999983516
},
"TrainerController.start_learning": {
"total": 1415.369753356,
"count": 1,
"self": 1.1768643800498921,
"children": {
"TrainerController._reset_env": {
"total": 3.5267676150000398,
"count": 1,
"self": 3.5267676150000398
},
"TrainerController.advance": {
"total": 1410.5270989579499,
"count": 45528,
"self": 1.278796179943356,
"children": {
"env_step": {
"total": 975.4345707480162,
"count": 45528,
"self": 737.3759738070293,
"children": {
"SubprocessEnvManager._take_step": {
"total": 237.30210188099807,
"count": 45528,
"self": 4.382743900990818,
"children": {
"TorchPolicy.evaluate": {
"total": 232.91935798000725,
"count": 45528,
"self": 232.91935798000725
}
}
},
"workers": {
"total": 0.7564950599888789,
"count": 45528,
"self": 0.0,
"children": {
"worker_root": {
"total": 1409.7750075159875,
"count": 45528,
"is_parallel": true,
"self": 767.8400091890122,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005722417000015412,
"count": 1,
"is_parallel": true,
"self": 0.003934103000005962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00178831400000945,
"count": 10,
"is_parallel": true,
"self": 0.00178831400000945
}
}
},
"UnityEnvironment.step": {
"total": 0.06942255399997066,
"count": 1,
"is_parallel": true,
"self": 0.0006197099999099009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004544550000673553,
"count": 1,
"is_parallel": true,
"self": 0.0004544550000673553
},
"communicator.exchange": {
"total": 0.06449577499995485,
"count": 1,
"is_parallel": true,
"self": 0.06449577499995485
},
"steps_from_proto": {
"total": 0.0038526140000385567,
"count": 1,
"is_parallel": true,
"self": 0.0007763969999814435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003076217000057113,
"count": 10,
"is_parallel": true,
"self": 0.003076217000057113
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 641.9349983269752,
"count": 45527,
"is_parallel": true,
"self": 30.38475657905053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 16.356370648996403,
"count": 45527,
"is_parallel": true,
"self": 16.356370648996403
},
"communicator.exchange": {
"total": 492.5751335959445,
"count": 45527,
"is_parallel": true,
"self": 492.5751335959445
},
"steps_from_proto": {
"total": 102.61873750298378,
"count": 45527,
"is_parallel": true,
"self": 18.97251356815775,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.64622393482603,
"count": 455270,
"is_parallel": true,
"self": 83.64622393482603
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 433.8137320299903,
"count": 45528,
"self": 1.5856018959825633,
"children": {
"process_trajectory": {
"total": 86.78463855200562,
"count": 45528,
"self": 85.14503117000595,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6396073819996673,
"count": 10,
"self": 1.6396073819996673
}
}
},
"_update_policy": {
"total": 345.44349158200214,
"count": 113,
"self": 176.4400933020097,
"children": {
"TorchPPOOptimizer.update": {
"total": 169.00339827999244,
"count": 9605,
"self": 169.00339827999244
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.089999366551638e-07,
"count": 1,
"self": 9.089999366551638e-07
},
"TrainerController._save_models": {
"total": 0.1390214940001897,
"count": 1,
"self": 0.0009906260002026102,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1380308679999871,
"count": 1,
"self": 0.1380308679999871
}
}
}
}
}
}
}