Harashi's picture
Huggy
0acd11a verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403067708015442,
"min": 1.403067708015442,
"max": 1.4262980222702026,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68873.7890625,
"min": 68618.3671875,
"max": 76272.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.16524701873935,
"min": 79.40836012861736,
"max": 396.7857142857143,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49405.0,
"min": 48909.0,
"max": 49995.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999968.0,
"min": 49752.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999968.0,
"min": 49752.0,
"max": 1999968.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4517736434936523,
"min": -0.009538774378597736,
"max": 2.511013984680176,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1439.191162109375,
"min": -1.1923468112945557,
"max": 1487.030517578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8561366634027716,
"min": 1.7781502044200896,
"max": 4.006355607570125,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2263.552221417427,
"min": 222.26877555251122,
"max": 2369.9971683621407,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8561366634027716,
"min": 1.7781502044200896,
"max": 4.006355607570125,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2263.552221417427,
"min": 222.26877555251122,
"max": 2369.9971683621407,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016520131413886297,
"min": 0.011028900158028893,
"max": 0.021966030557329458,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04956039424165889,
"min": 0.022057800316057787,
"max": 0.05775428650182827,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06369795604712435,
"min": 0.022753377351909874,
"max": 0.06379144415259361,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19109386814137302,
"min": 0.04550675470381975,
"max": 0.19109386814137302,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.464198845299992e-06,
"min": 3.464198845299992e-06,
"max": 0.0002953634265455249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0392596535899977e-05,
"min": 1.0392596535899977e-05,
"max": 0.0008439952686682499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115469999999999,
"min": 0.10115469999999999,
"max": 0.19845447500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30346409999999996,
"min": 0.20749825,
"max": 0.5813317499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.761952999999987e-05,
"min": 6.761952999999987e-05,
"max": 0.004922878302500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020285858999999958,
"min": 0.00020285858999999958,
"max": 0.014068454325000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750530364",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750532786"
},
"total": 2421.338126527,
"count": 1,
"self": 0.4884207449999849,
"children": {
"run_training.setup": {
"total": 0.025650417000065318,
"count": 1,
"self": 0.025650417000065318
},
"TrainerController.start_learning": {
"total": 2420.824055365,
"count": 1,
"self": 4.126889297988782,
"children": {
"TrainerController._reset_env": {
"total": 3.1230046530000664,
"count": 1,
"self": 3.1230046530000664
},
"TrainerController.advance": {
"total": 2413.4548051250113,
"count": 232755,
"self": 4.385123549925993,
"children": {
"env_step": {
"total": 1924.1606161810382,
"count": 232755,
"self": 1524.2707496842268,
"children": {
"SubprocessEnvManager._take_step": {
"total": 397.3211660338293,
"count": 232755,
"self": 14.7125025898805,
"children": {
"TorchPolicy.evaluate": {
"total": 382.6086634439488,
"count": 222902,
"self": 382.6086634439488
}
}
},
"workers": {
"total": 2.5687004629821786,
"count": 232755,
"self": 0.0,
"children": {
"worker_root": {
"total": 2413.569855922861,
"count": 232755,
"is_parallel": true,
"self": 1169.24473436586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008691670000189333,
"count": 1,
"is_parallel": true,
"self": 0.00028153000005204376,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005876369999668896,
"count": 2,
"is_parallel": true,
"self": 0.0005876369999668896
}
}
},
"UnityEnvironment.step": {
"total": 0.03135846899999706,
"count": 1,
"is_parallel": true,
"self": 0.00028824700007135107,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001910870000756404,
"count": 1,
"is_parallel": true,
"self": 0.0001910870000756404
},
"communicator.exchange": {
"total": 0.03024401199991189,
"count": 1,
"is_parallel": true,
"self": 0.03024401199991189
},
"steps_from_proto": {
"total": 0.0006351229999381758,
"count": 1,
"is_parallel": true,
"self": 0.00017979400001877366,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004553289999194021,
"count": 2,
"is_parallel": true,
"self": 0.0004553289999194021
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1244.3251215570008,
"count": 232754,
"is_parallel": true,
"self": 36.91960732084681,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.23864309114674,
"count": 232754,
"is_parallel": true,
"self": 80.23864309114674
},
"communicator.exchange": {
"total": 1040.2600599580146,
"count": 232754,
"is_parallel": true,
"self": 1040.2600599580146
},
"steps_from_proto": {
"total": 86.90681118699274,
"count": 232754,
"is_parallel": true,
"self": 32.18229590299825,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.72451528399449,
"count": 465508,
"is_parallel": true,
"self": 54.72451528399449
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.9090653940468,
"count": 232755,
"self": 6.452826622012822,
"children": {
"process_trajectory": {
"total": 160.2324738340344,
"count": 232755,
"self": 157.9242083240348,
"children": {
"RLTrainer._checkpoint": {
"total": 2.3082655099996146,
"count": 20,
"self": 2.3082655099996146
}
}
},
"_update_policy": {
"total": 318.2237649379996,
"count": 97,
"self": 254.7660244619866,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.45774047601299,
"count": 2910,
"self": 63.45774047601299
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.51999936660286e-07,
"count": 1,
"self": 9.51999936660286e-07
},
"TrainerController._save_models": {
"total": 0.1193553369998881,
"count": 1,
"self": 0.0017264849998355203,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11762885200005258,
"count": 1,
"self": 0.11762885200005258
}
}
}
}
}
}
}