YoriV's picture
First training of SnowballTarget
fbed49d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0198674201965332,
"min": 1.0198674201965332,
"max": 2.855074644088745,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9737.6943359375,
"min": 9737.6943359375,
"max": 29238.818359375,
"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": 1.3228753805160522,
"min": 0.13206645846366882,
"max": 1.3228753805160522,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 257.960693359375,
"min": 25.620891571044922,
"max": 266.75994873046875,
"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": 0.06880673235305128,
"min": 0.062485644104776396,
"max": 0.07166656887359162,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2752269294122051,
"min": 0.2587989130823225,
"max": 0.3523808842534587,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.09597188647032953,
"min": 0.04459270044083265,
"max": 0.10475257605898614,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3838875458813181,
"min": 0.1783708017633306,
"max": 0.5237628802949307,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999997,
"min": 0.10269399999999997,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077599999999986,
"min": 0.41077599999999986,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.818181818181817,
"min": 3.6363636363636362,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 160.0,
"max": 1423.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.6363636363636362,
"max": 25.87272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 160.0,
"max": 1423.0,
"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": "1676211653",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676212236"
},
"total": 583.657872903,
"count": 1,
"self": 0.38910154300003796,
"children": {
"run_training.setup": {
"total": 0.1737851130000081,
"count": 1,
"self": 0.1737851130000081
},
"TrainerController.start_learning": {
"total": 583.094986247,
"count": 1,
"self": 0.5975753059963154,
"children": {
"TrainerController._reset_env": {
"total": 9.74378096800001,
"count": 1,
"self": 9.74378096800001
},
"TrainerController.advance": {
"total": 572.6248478790036,
"count": 18202,
"self": 0.334344441005328,
"children": {
"env_step": {
"total": 572.2905034379983,
"count": 18202,
"self": 422.5320722490079,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.45217664799122,
"count": 18202,
"self": 1.6320114369901262,
"children": {
"TorchPolicy.evaluate": {
"total": 147.8201652110011,
"count": 18202,
"self": 34.14470514800428,
"children": {
"TorchPolicy.sample_actions": {
"total": 113.67546006299682,
"count": 18202,
"self": 113.67546006299682
}
}
}
}
},
"workers": {
"total": 0.3062545409991344,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 581.3727387960016,
"count": 18202,
"is_parallel": true,
"self": 326.6227091340126,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006255031000023337,
"count": 1,
"is_parallel": true,
"self": 0.003265414000054534,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029896169999688027,
"count": 10,
"is_parallel": true,
"self": 0.0029896169999688027
}
}
},
"UnityEnvironment.step": {
"total": 0.05259773400001677,
"count": 1,
"is_parallel": true,
"self": 0.00040162999999893145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003131230000121832,
"count": 1,
"is_parallel": true,
"self": 0.0003131230000121832
},
"communicator.exchange": {
"total": 0.050048844000002646,
"count": 1,
"is_parallel": true,
"self": 0.050048844000002646
},
"steps_from_proto": {
"total": 0.001834137000003011,
"count": 1,
"is_parallel": true,
"self": 0.0004241470000465597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014099899999564514,
"count": 10,
"is_parallel": true,
"self": 0.0014099899999564514
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.750029661989,
"count": 18201,
"is_parallel": true,
"self": 10.099201741992886,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.762373139990359,
"count": 18201,
"is_parallel": true,
"self": 5.762373139990359
},
"communicator.exchange": {
"total": 203.31999586101108,
"count": 18201,
"is_parallel": true,
"self": 203.31999586101108
},
"steps_from_proto": {
"total": 35.56845891899468,
"count": 18201,
"is_parallel": true,
"self": 7.721189165988449,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.84726975300623,
"count": 182010,
"is_parallel": true,
"self": 27.84726975300623
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000164091999977245,
"count": 1,
"self": 0.000164091999977245,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 569.0813978520299,
"count": 419470,
"is_parallel": true,
"self": 10.72172313904207,
"children": {
"process_trajectory": {
"total": 272.2748173709881,
"count": 419470,
"is_parallel": true,
"self": 271.4526787139882,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8221386569999254,
"count": 4,
"is_parallel": true,
"self": 0.8221386569999254
}
}
},
"_update_policy": {
"total": 286.08485734199974,
"count": 90,
"is_parallel": true,
"self": 116.39482031700447,
"children": {
"TorchPPOOptimizer.update": {
"total": 169.69003702499526,
"count": 9174,
"is_parallel": true,
"self": 169.69003702499526
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1286180020000529,
"count": 1,
"self": 0.0009030350000784892,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12771496699997442,
"count": 1,
"self": 0.12771496699997442
}
}
}
}
}
}
}