feabries's picture
First training of SnowballTarget
5e78720
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8860079050064087,
"min": 0.8860079050064087,
"max": 2.8698313236236572,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8469.349609375,
"min": 8469.349609375,
"max": 29389.94140625,
"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": 12.787835121154785,
"min": 0.26366567611694336,
"max": 12.838927268981934,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.6279296875,
"min": 51.15114212036133,
"max": 2631.134033203125,
"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": 0.07075399967645496,
"min": 0.06378912401117964,
"max": 0.0740203506870517,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28301599870581984,
"min": 0.25815888609527154,
"max": 0.36707624483753143,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17405089180843503,
"min": 0.10853735970986057,
"max": 0.302619092838437,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6962035672337401,
"min": 0.4341494388394423,
"max": 1.513095464192185,
"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": 3.1136363636363638,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 137.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.1136363636363638,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 137.0,
"max": 1391.0,
"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": "1680103168",
"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",
"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": "1680103656"
},
"total": 488.136144198,
"count": 1,
"self": 0.43074210899999343,
"children": {
"run_training.setup": {
"total": 0.11160531600012291,
"count": 1,
"self": 0.11160531600012291
},
"TrainerController.start_learning": {
"total": 487.5937967729999,
"count": 1,
"self": 0.532070416994884,
"children": {
"TrainerController._reset_env": {
"total": 9.38637658000016,
"count": 1,
"self": 9.38637658000016
},
"TrainerController.advance": {
"total": 477.5409095690047,
"count": 18202,
"self": 0.2920827140003439,
"children": {
"env_step": {
"total": 477.2488268550044,
"count": 18202,
"self": 341.5446773839917,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.4282974369969,
"count": 18202,
"self": 2.612954557996318,
"children": {
"TorchPolicy.evaluate": {
"total": 132.81534287900058,
"count": 18202,
"self": 132.81534287900058
}
}
},
"workers": {
"total": 0.2758520340157702,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 486.05929848298956,
"count": 18202,
"is_parallel": true,
"self": 235.0843154819845,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0044437740000375925,
"count": 1,
"is_parallel": true,
"self": 0.0029262860000471846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015174879999904078,
"count": 10,
"is_parallel": true,
"self": 0.0015174879999904078
}
}
},
"UnityEnvironment.step": {
"total": 0.1109460580000814,
"count": 1,
"is_parallel": true,
"self": 0.000601271000050474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004478740002014092,
"count": 1,
"is_parallel": true,
"self": 0.0004478740002014092
},
"communicator.exchange": {
"total": 0.10791486199991596,
"count": 1,
"is_parallel": true,
"self": 0.10791486199991596
},
"steps_from_proto": {
"total": 0.001982050999913554,
"count": 1,
"is_parallel": true,
"self": 0.0004995090002921643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014825419996213896,
"count": 10,
"is_parallel": true,
"self": 0.0014825419996213896
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.97498300100506,
"count": 18201,
"is_parallel": true,
"self": 10.30537539400575,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.633464747993457,
"count": 18201,
"is_parallel": true,
"self": 5.633464747993457
},
"communicator.exchange": {
"total": 200.66625279800814,
"count": 18201,
"is_parallel": true,
"self": 200.66625279800814
},
"steps_from_proto": {
"total": 34.369890060997704,
"count": 18201,
"is_parallel": true,
"self": 6.833336761951159,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.536553299046545,
"count": 182010,
"is_parallel": true,
"self": 27.536553299046545
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010662599993338517,
"count": 1,
"self": 0.00010662599993338517,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 473.4363843899796,
"count": 433790,
"is_parallel": true,
"self": 11.525867482956983,
"children": {
"process_trajectory": {
"total": 264.70807909002383,
"count": 433790,
"is_parallel": true,
"self": 263.5006698760237,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2074092140001085,
"count": 4,
"is_parallel": true,
"self": 1.2074092140001085
}
}
},
"_update_policy": {
"total": 197.20243781699878,
"count": 90,
"is_parallel": true,
"self": 71.25791387300796,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.94452394399082,
"count": 4584,
"is_parallel": true,
"self": 125.94452394399082
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13433358100019177,
"count": 1,
"self": 0.0016366510001262213,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13269693000006555,
"count": 1,
"self": 0.13269693000006555
}
}
}
}
}
}
}