ThoDum's picture
Longer training
a156aa8
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0141493082046509,
"min": 1.0028049945831299,
"max": 2.331270933151245,
"count": 80
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9694.2529296875,
"min": 9694.2529296875,
"max": 24054.0546875,
"count": 80
},
"SnowballTarget.Step.mean": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Step.sum": {
"value": 999992.0,
"min": 209936.0,
"max": 999992.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 24.8193302154541,
"min": 3.757380723953247,
"max": 24.8193302154541,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4839.76953125,
"min": 721.4171142578125,
"max": 5064.43115234375,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 80
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.5,
"min": 13.022727272727273,
"max": 26.681818181818183,
"count": 80
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1166.0,
"min": 573.0,
"max": 1461.0,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.5,
"min": 13.022727272727273,
"max": 26.681818181818183,
"count": 80
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1166.0,
"min": 573.0,
"max": 1461.0,
"count": 80
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 80
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03426832367000069,
"min": 0.03102098718976997,
"max": 0.039631483169311345,
"count": 47
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.03426832367000069,
"min": 0.03102098718976997,
"max": 0.039631483169311345,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18965871554488936,
"min": 0.18965871554488936,
"max": 0.37981617571127535,
"count": 47
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.18965871554488936,
"min": 0.18965871554488936,
"max": 0.37981617571127535,
"count": 47
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.392899202399995e-06,
"min": 2.392899202399995e-06,
"max": 0.00023492402169199996,
"count": 47
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.392899202399995e-06,
"min": 2.392899202399995e-06,
"max": 0.00023492402169199996,
"count": 47
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1007976,
"min": 0.1007976,
"max": 0.178308,
"count": 47
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1007976,
"min": 0.1007976,
"max": 0.178308,
"count": 47
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.980023999999992e-05,
"min": 4.980023999999992e-05,
"max": 0.003917569199999999,
"count": 47
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.980023999999992e-05,
"min": 4.980023999999992e-05,
"max": 0.003917569199999999,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678798791",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1678801523"
},
"total": 2732.633331156,
"count": 1,
"self": 0.5795033780000267,
"children": {
"run_training.setup": {
"total": 0.14261974400005784,
"count": 1,
"self": 0.14261974400005784
},
"TrainerController.start_learning": {
"total": 2731.911208034,
"count": 1,
"self": 4.257480065026812,
"children": {
"TrainerController._reset_env": {
"total": 4.930865503999939,
"count": 1,
"self": 4.930865503999939
},
"TrainerController.advance": {
"total": 2722.5292971629733,
"count": 72743,
"self": 1.9722689669802094,
"children": {
"env_step": {
"total": 2720.557028195993,
"count": 72743,
"self": 2223.567314524952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 494.99194302702585,
"count": 72743,
"self": 20.876947233994088,
"children": {
"TorchPolicy.evaluate": {
"total": 474.11499579303177,
"count": 72743,
"self": 474.11499579303177
}
}
},
"workers": {
"total": 1.997770644015418,
"count": 72743,
"self": 0.0,
"children": {
"worker_root": {
"total": 2721.622313828897,
"count": 72743,
"is_parallel": true,
"self": 1232.611625464882,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003233468000189532,
"count": 1,
"is_parallel": true,
"self": 0.0010498329997972178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021836350003923144,
"count": 10,
"is_parallel": true,
"self": 0.0021836350003923144
}
}
},
"UnityEnvironment.step": {
"total": 0.1143543860000591,
"count": 1,
"is_parallel": true,
"self": 0.000648160000309872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004254459997810045,
"count": 1,
"is_parallel": true,
"self": 0.0004254459997810045
},
"communicator.exchange": {
"total": 0.11080841299985877,
"count": 1,
"is_parallel": true,
"self": 0.11080841299985877
},
"steps_from_proto": {
"total": 0.0024723670001094433,
"count": 1,
"is_parallel": true,
"self": 0.0005268710003747401,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019454959997347032,
"count": 10,
"is_parallel": true,
"self": 0.0019454959997347032
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1489.0106883640149,
"count": 72742,
"is_parallel": true,
"self": 59.252631996040236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 32.72857025408143,
"count": 72742,
"is_parallel": true,
"self": 32.72857025408143
},
"communicator.exchange": {
"total": 1205.52390911198,
"count": 72742,
"is_parallel": true,
"self": 1205.52390911198
},
"steps_from_proto": {
"total": 191.50557700191325,
"count": 72742,
"is_parallel": true,
"self": 41.471629434738816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 150.03394756717444,
"count": 727420,
"is_parallel": true,
"self": 150.03394756717444
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00029105799967510393,
"count": 1,
"self": 0.00029105799967510393,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2685.411340076746,
"count": 3855853,
"is_parallel": true,
"self": 102.16043895567736,
"children": {
"process_trajectory": {
"total": 1983.1800530920686,
"count": 3855853,
"is_parallel": true,
"self": 1976.2971148120685,
"children": {
"RLTrainer._checkpoint": {
"total": 6.8829382800001895,
"count": 16,
"is_parallel": true,
"self": 6.8829382800001895
}
}
},
"_update_policy": {
"total": 600.070848029,
"count": 47,
"is_parallel": true,
"self": 302.5348754579927,
"children": {
"TorchPPOOptimizer.update": {
"total": 297.5359725710073,
"count": 4599,
"is_parallel": true,
"self": 297.5359725710073
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19327424400034943,
"count": 1,
"self": 0.0031978820006770547,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19007636199967237,
"count": 1,
"self": 0.19007636199967237
}
}
}
}
}
}
}