MHaurel's picture
First Push
75ce360
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8870654702186584,
"min": 0.8620541095733643,
"max": 2.8408126831054688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8469.701171875,
"min": 8469.701171875,
"max": 29092.76171875,
"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": 12.686056137084961,
"min": 0.41136497259140015,
"max": 12.686056137084961,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2473.781005859375,
"min": 79.80480194091797,
"max": 2573.939453125,
"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": 0.061476044411606645,
"min": 0.061476044411606645,
"max": 0.07451666136301927,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24590417764642658,
"min": 0.24590417764642658,
"max": 0.3633660146140256,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18659205274546847,
"min": 0.13107580909911798,
"max": 0.26302051176043123,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7463682109818739,
"min": 0.5243032363964719,
"max": 1.315102558802156,
"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": 25.204545454545453,
"min": 3.6363636363636362,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 160.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.6363636363636362,
"max": 25.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 160.0,
"max": 1375.0,
"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": "1675284238",
"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": "1675284681"
},
"total": 443.73945220099995,
"count": 1,
"self": 0.3924156719999701,
"children": {
"run_training.setup": {
"total": 0.10012755700000753,
"count": 1,
"self": 0.10012755700000753
},
"TrainerController.start_learning": {
"total": 443.24690897199997,
"count": 1,
"self": 0.5397125700051788,
"children": {
"TrainerController._reset_env": {
"total": 9.561460264999994,
"count": 1,
"self": 9.561460264999994
},
"TrainerController.advance": {
"total": 433.0278925789948,
"count": 18204,
"self": 0.3007322399971599,
"children": {
"env_step": {
"total": 432.72716033899763,
"count": 18204,
"self": 281.9287229049972,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.5215196820056,
"count": 18204,
"self": 1.4829878940017807,
"children": {
"TorchPolicy.evaluate": {
"total": 149.0385317880038,
"count": 18204,
"self": 33.45509452601078,
"children": {
"TorchPolicy.sample_actions": {
"total": 115.58343726199303,
"count": 18204,
"self": 115.58343726199303
}
}
}
}
},
"workers": {
"total": 0.27691775199485846,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.90910171600353,
"count": 18204,
"is_parallel": true,
"self": 214.39769997201347,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006278854000015599,
"count": 1,
"is_parallel": true,
"self": 0.0038313810000545345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024474729999610645,
"count": 10,
"is_parallel": true,
"self": 0.0024474729999610645
}
}
},
"UnityEnvironment.step": {
"total": 0.0366159410000364,
"count": 1,
"is_parallel": true,
"self": 0.0006181300000207557,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003956670000206941,
"count": 1,
"is_parallel": true,
"self": 0.0003956670000206941
},
"communicator.exchange": {
"total": 0.033620389999953204,
"count": 1,
"is_parallel": true,
"self": 0.033620389999953204
},
"steps_from_proto": {
"total": 0.0019817540000417466,
"count": 1,
"is_parallel": true,
"self": 0.0004202119999945353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015615420000472113,
"count": 10,
"is_parallel": true,
"self": 0.0015615420000472113
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.51140174399006,
"count": 18203,
"is_parallel": true,
"self": 8.548597152978743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.260308882011543,
"count": 18203,
"is_parallel": true,
"self": 5.260308882011543
},
"communicator.exchange": {
"total": 181.9951889849932,
"count": 18203,
"is_parallel": true,
"self": 181.9951889849932
},
"steps_from_proto": {
"total": 31.70730672400657,
"count": 18203,
"is_parallel": true,
"self": 6.814297757019176,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.893008966987395,
"count": 182030,
"is_parallel": true,
"self": 24.893008966987395
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.029800001921103e-05,
"count": 1,
"self": 5.029800001921103e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 429.79007806803605,
"count": 354342,
"is_parallel": true,
"self": 9.914216695997254,
"children": {
"process_trajectory": {
"total": 247.43639301503902,
"count": 354342,
"is_parallel": true,
"self": 246.6924610800391,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7439319349999209,
"count": 4,
"is_parallel": true,
"self": 0.7439319349999209
}
}
},
"_update_policy": {
"total": 172.43946835699978,
"count": 90,
"is_parallel": true,
"self": 40.61622697199948,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.8232413850003,
"count": 4587,
"is_parallel": true,
"self": 131.8232413850003
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11779325999998491,
"count": 1,
"self": 0.0008245079999369409,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11696875200004797,
"count": 1,
"self": 0.11696875200004797
}
}
}
}
}
}
}