numan966's picture
First training of snowball
6335b94
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8022074103355408,
"min": 0.8022074103355408,
"max": 2.8657073974609375,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7659.4765625,
"min": 7659.4765625,
"max": 29347.708984375,
"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": 11.97554874420166,
"min": 0.3689185380935669,
"max": 11.97554874420166,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2335.23193359375,
"min": 71.57019805908203,
"max": 2404.53759765625,
"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": 0.07378336568374425,
"min": 0.0626596626026702,
"max": 0.07713360725371304,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.295133462734977,
"min": 0.2506386504106808,
"max": 0.37663965720646814,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20992917786626253,
"min": 0.12742587386666998,
"max": 0.28347645794936255,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8397167114650501,
"min": 0.5097034954666799,
"max": 1.3124841273415322,
"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": 2.320060000000001e-05,
"min": 2.320060000000001e-05,
"max": 0.00048674060000000003,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 9.280240000000004e-05,
"min": 9.280240000000004e-05,
"max": 0.002312428,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.181818181818183,
"min": 3.409090909090909,
"max": 24.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1064.0,
"min": 150.0,
"max": 1280.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.181818181818183,
"min": 3.409090909090909,
"max": 24.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1064.0,
"min": 150.0,
"max": 1280.0,
"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": "1673561221",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673561657"
},
"total": 435.58335853599965,
"count": 1,
"self": 0.4355719419995694,
"children": {
"run_training.setup": {
"total": 0.11020175300018309,
"count": 1,
"self": 0.11020175300018309
},
"TrainerController.start_learning": {
"total": 435.0375848409999,
"count": 1,
"self": 0.5419784480109229,
"children": {
"TrainerController._reset_env": {
"total": 9.292773897000188,
"count": 1,
"self": 9.292773897000188
},
"TrainerController.advance": {
"total": 425.0805251349884,
"count": 18204,
"self": 0.26959132001366015,
"children": {
"env_step": {
"total": 424.81093381497476,
"count": 18204,
"self": 278.26072068694066,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.27184664199513,
"count": 18204,
"self": 1.3690101150195915,
"children": {
"TorchPolicy.evaluate": {
"total": 144.90283652697553,
"count": 18204,
"self": 32.84957137697347,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.05326515000206,
"count": 18204,
"self": 112.05326515000206
}
}
}
}
},
"workers": {
"total": 0.2783664860389763,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.77187296398824,
"count": 18204,
"is_parallel": true,
"self": 208.6985145110075,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008329983000294305,
"count": 1,
"is_parallel": true,
"self": 0.004334574000495195,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0039954089997991105,
"count": 10,
"is_parallel": true,
"self": 0.0039954089997991105
}
}
},
"UnityEnvironment.step": {
"total": 0.036314907999894785,
"count": 1,
"is_parallel": true,
"self": 0.0005249459995866346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040317999992112163,
"count": 1,
"is_parallel": true,
"self": 0.00040317999992112163
},
"communicator.exchange": {
"total": 0.03346855700010565,
"count": 1,
"is_parallel": true,
"self": 0.03346855700010565
},
"steps_from_proto": {
"total": 0.0019182250002813817,
"count": 1,
"is_parallel": true,
"self": 0.00042714400160548394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014910809986758977,
"count": 10,
"is_parallel": true,
"self": 0.0014910809986758977
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.07335845298076,
"count": 18203,
"is_parallel": true,
"self": 8.510852205976335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.9601330029790915,
"count": 18203,
"is_parallel": true,
"self": 4.9601330029790915
},
"communicator.exchange": {
"total": 178.65614209103296,
"count": 18203,
"is_parallel": true,
"self": 178.65614209103296
},
"steps_from_proto": {
"total": 32.94623115299237,
"count": 18203,
"is_parallel": true,
"self": 6.752926656857198,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.19330449613517,
"count": 182030,
"is_parallel": true,
"self": 26.19330449613517
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.539600013231393e-05,
"count": 1,
"self": 4.539600013231393e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 422.14358989012453,
"count": 339160,
"is_parallel": true,
"self": 8.995773771154745,
"children": {
"process_trajectory": {
"total": 241.11545385097043,
"count": 339160,
"is_parallel": true,
"self": 240.3810664499706,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7343874009998217,
"count": 4,
"is_parallel": true,
"self": 0.7343874009998217
}
}
},
"_update_policy": {
"total": 172.03236226799936,
"count": 90,
"is_parallel": true,
"self": 44.819321700998444,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.21304056700092,
"count": 4587,
"is_parallel": true,
"self": 127.21304056700092
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12226196500023434,
"count": 1,
"self": 0.0008851600005073124,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12137680499972703,
"count": 1,
"self": 0.12137680499972703
}
}
}
}
}
}
}