hiboujoyeux's picture
First Push
5ea8da7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.002406358718872,
"min": 1.002406358718872,
"max": 2.860771656036377,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9526.8701171875,
"min": 9526.8701171875,
"max": 29202.755859375,
"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": 13.390494346618652,
"min": 0.37632235884666443,
"max": 13.390494346618652,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2611.146484375,
"min": 73.00653839111328,
"max": 2718.173828125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06719212111605813,
"min": 0.06224831449419392,
"max": 0.07339277994892031,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2687684844642325,
"min": 0.24899325797677568,
"max": 0.36696389974460153,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17851408695181212,
"min": 0.1298146729914508,
"max": 0.289025989057971,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7140563478072485,
"min": 0.5192586919658032,
"max": 1.445129945289855,
"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.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.Environment.CumulativeReward.mean": {
"value": 26.386363636363637,
"min": 3.5681818181818183,
"max": 26.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1161.0,
"min": 157.0,
"max": 1455.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.386363636363637,
"min": 3.5681818181818183,
"max": 26.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1161.0,
"min": 157.0,
"max": 1455.0,
"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": "1772200314",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1772200768"
},
"total": 454.2938056889998,
"count": 1,
"self": 0.4302031789998182,
"children": {
"run_training.setup": {
"total": 0.024804351000057068,
"count": 1,
"self": 0.024804351000057068
},
"TrainerController.start_learning": {
"total": 453.8387981589999,
"count": 1,
"self": 0.3861987070408759,
"children": {
"TrainerController._reset_env": {
"total": 2.8952263159999347,
"count": 1,
"self": 2.8952263159999347
},
"TrainerController.advance": {
"total": 450.4834491699594,
"count": 18192,
"self": 0.39633448595759546,
"children": {
"env_step": {
"total": 326.25457670103515,
"count": 18192,
"self": 255.36660082704657,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.64357784199365,
"count": 18192,
"self": 1.2923378219752522,
"children": {
"TorchPolicy.evaluate": {
"total": 69.3512400200184,
"count": 18192,
"self": 69.3512400200184
}
}
},
"workers": {
"total": 0.24439803199493326,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.84302895695555,
"count": 18192,
"is_parallel": true,
"self": 227.95604478189443,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0045386580000013055,
"count": 1,
"is_parallel": true,
"self": 0.0032228970012511127,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013157609987501928,
"count": 10,
"is_parallel": true,
"self": 0.0013157609987501928
}
}
},
"UnityEnvironment.step": {
"total": 0.04582102699987445,
"count": 1,
"is_parallel": true,
"self": 0.0005867169998055033,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041415700025027036,
"count": 1,
"is_parallel": true,
"self": 0.00041415700025027036
},
"communicator.exchange": {
"total": 0.04099638199977562,
"count": 1,
"is_parallel": true,
"self": 0.04099638199977562
},
"steps_from_proto": {
"total": 0.0038237710000430525,
"count": 1,
"is_parallel": true,
"self": 0.0003544970013535931,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0034692739986894594,
"count": 10,
"is_parallel": true,
"self": 0.0034692739986894594
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.88698417506112,
"count": 18191,
"is_parallel": true,
"self": 10.388089776035486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.515268026985723,
"count": 18191,
"is_parallel": true,
"self": 5.515268026985723
},
"communicator.exchange": {
"total": 171.68139677700674,
"count": 18191,
"is_parallel": true,
"self": 171.68139677700674
},
"steps_from_proto": {
"total": 36.30222959503317,
"count": 18191,
"is_parallel": true,
"self": 6.672140700960881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.630088894072287,
"count": 181910,
"is_parallel": true,
"self": 29.630088894072287
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.83253798296664,
"count": 18192,
"self": 0.5107215569564687,
"children": {
"process_trajectory": {
"total": 26.653242603008948,
"count": 18192,
"self": 26.280476796009225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3727658069997233,
"count": 4,
"self": 0.3727658069997233
}
}
},
"_update_policy": {
"total": 96.66857382300122,
"count": 90,
"self": 39.68908853801531,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.97948528498591,
"count": 4587,
"self": 56.97948528498591
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.149998732027598e-07,
"count": 1,
"self": 9.149998732027598e-07
},
"TrainerController._save_models": {
"total": 0.07392305099983787,
"count": 1,
"self": 0.0006796929997108236,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07324335800012705,
"count": 1,
"self": 0.07324335800012705
}
}
}
}
}
}
}