gyaan's picture
First Push
61084b3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9753860235214233,
"min": 0.9472404718399048,
"max": 2.8697831630706787,
"count": 30
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10042.57421875,
"min": 9196.828125,
"max": 29294.74609375,
"count": 30
},
"SnowballTarget.Step.mean": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Step.sum": {
"value": 299968.0,
"min": 9952.0,
"max": 299968.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.059721946716309,
"min": 0.1935761421918869,
"max": 13.059721946716309,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2664.183349609375,
"min": 37.55377197265625,
"max": 2664.183349609375,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 30
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.836363636363636,
"min": 2.227272727272727,
"max": 26.181818181818183,
"count": 30
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1421.0,
"min": 98.0,
"max": 1421.0,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.836363636363636,
"min": 2.227272727272727,
"max": 26.181818181818183,
"count": 30
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1421.0,
"min": 98.0,
"max": 1421.0,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0481321936909998,
"min": 0.04245606272974435,
"max": 0.059823862057265954,
"count": 30
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.1443965810729994,
"min": 0.0849121254594887,
"max": 0.15895099283935613,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19496405562933752,
"min": 0.07049298695489473,
"max": 0.31274926633227107,
"count": 30
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5848921668880126,
"min": 0.14098597390978945,
"max": 0.8923786007890515,
"count": 30
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 5.288098237333326e-06,
"min": 5.288098237333326e-06,
"max": 0.00029348800217066665,
"count": 30
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5864294711999978e-05,
"min": 1.5864294711999978e-05,
"max": 0.0007946640351119999,
"count": 30
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1021152,
"min": 0.1021152,
"max": 0.21739519999999998,
"count": 30
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.3063456,
"min": 0.21303040000000004,
"max": 0.6178656,
"count": 30
},
"SnowballTarget.Policy.Beta.mean": {
"value": 9.795706666666657e-05,
"min": 9.795706666666657e-05,
"max": 0.004891683733333334,
"count": 30
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002938711999999997,
"min": 0.0002938711999999997,
"max": 0.0132479112,
"count": 30
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739087954",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739088543"
},
"total": 589.2264441479999,
"count": 1,
"self": 0.7044272649995946,
"children": {
"run_training.setup": {
"total": 0.023291454000172962,
"count": 1,
"self": 0.023291454000172962
},
"TrainerController.start_learning": {
"total": 588.4987254290002,
"count": 1,
"self": 0.48681453698122823,
"children": {
"TrainerController._reset_env": {
"total": 3.1069359509999686,
"count": 1,
"self": 3.1069359509999686
},
"TrainerController.advance": {
"total": 584.770974480019,
"count": 27328,
"self": 0.5067600410184241,
"children": {
"env_step": {
"total": 436.53024826700585,
"count": 27328,
"self": 331.3877047069816,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.84639007202372,
"count": 27328,
"self": 1.8468051290315088,
"children": {
"TorchPolicy.evaluate": {
"total": 102.99958494299221,
"count": 27328,
"self": 102.99958494299221
}
}
},
"workers": {
"total": 0.29615348800052743,
"count": 27328,
"self": 0.0,
"children": {
"worker_root": {
"total": 586.3753860329837,
"count": 27328,
"is_parallel": true,
"self": 295.6327935679926,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0058125390000896004,
"count": 1,
"is_parallel": true,
"self": 0.00426044400023784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015520949998517608,
"count": 10,
"is_parallel": true,
"self": 0.0015520949998517608
}
}
},
"UnityEnvironment.step": {
"total": 0.03477160499983256,
"count": 1,
"is_parallel": true,
"self": 0.0005784259994925378,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038468599996122066,
"count": 1,
"is_parallel": true,
"self": 0.00038468599996122066
},
"communicator.exchange": {
"total": 0.0319951150001998,
"count": 1,
"is_parallel": true,
"self": 0.0319951150001998
},
"steps_from_proto": {
"total": 0.001813378000179,
"count": 1,
"is_parallel": true,
"self": 0.00038986200024737627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014235159999316238,
"count": 10,
"is_parallel": true,
"self": 0.0014235159999316238
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 290.74259246499105,
"count": 27327,
"is_parallel": true,
"self": 14.036682838001752,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.940820036003515,
"count": 27327,
"is_parallel": true,
"self": 7.940820036003515
},
"communicator.exchange": {
"total": 223.42978609298575,
"count": 27327,
"is_parallel": true,
"self": 223.42978609298575
},
"steps_from_proto": {
"total": 45.33530349800003,
"count": 27327,
"is_parallel": true,
"self": 7.955771116025517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.379532381974514,
"count": 273270,
"is_parallel": true,
"self": 37.379532381974514
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 147.73396617199478,
"count": 27328,
"self": 0.5817024239779585,
"children": {
"process_trajectory": {
"total": 40.43353507301822,
"count": 27328,
"self": 39.66406052601792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7694745470002999,
"count": 6,
"self": 0.7694745470002999
}
}
},
"_update_policy": {
"total": 106.7187286749986,
"count": 68,
"self": 59.1874309990053,
"children": {
"TorchPPOOptimizer.update": {
"total": 47.5312976759933,
"count": 3465,
"self": 47.5312976759933
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2999998943996616e-06,
"count": 1,
"self": 1.2999998943996616e-06
},
"TrainerController._save_models": {
"total": 0.13399916100001974,
"count": 1,
"self": 0.0012042000000747066,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13279496099994503,
"count": 1,
"self": 0.13279496099994503
}
}
}
}
}
}
}