mvyboh's picture
Huggy
c1866e8 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4079588651657104,
"min": 1.4079588651657104,
"max": 1.4283980131149292,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71016.0390625,
"min": 69032.5625,
"max": 77281.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 129.13802083333334,
"min": 91.41774491682071,
"max": 392.93700787401576,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49589.0,
"min": 48969.0,
"max": 50233.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999970.0,
"min": 49936.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999970.0,
"min": 49936.0,
"max": 1999970.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2234575748443604,
"min": 0.10401720553636551,
"max": 2.435297966003418,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 853.8077392578125,
"min": 13.106167793273926,
"max": 1272.564453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3214866345127425,
"min": 1.8497791123532115,
"max": 3.966170762976011,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1275.450867652893,
"min": 233.07216815650463,
"max": 2029.525236070156,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3214866345127425,
"min": 1.8497791123532115,
"max": 3.966170762976011,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1275.450867652893,
"min": 233.07216815650463,
"max": 2029.525236070156,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017512856173076824,
"min": 0.013626894128537969,
"max": 0.020490683669716722,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03502571234615365,
"min": 0.027253788257075938,
"max": 0.06100603648810647,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03957296091442307,
"min": 0.022514829225838185,
"max": 0.06483382085959116,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07914592182884614,
"min": 0.04502965845167637,
"max": 0.1731316135575374,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.40042353322501e-06,
"min": 4.40042353322501e-06,
"max": 0.000295367626544125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.80084706645002e-06,
"min": 8.80084706645002e-06,
"max": 0.0008442558185814001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10146677500000001,
"min": 0.10146677500000001,
"max": 0.198455875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20293355000000002,
"min": 0.20293355000000002,
"max": 0.5814185999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.319207250000018e-05,
"min": 8.319207250000018e-05,
"max": 0.0049229481624999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016638414500000037,
"min": 0.00016638414500000037,
"max": 0.014072788139999997,
"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": "1748426915",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748429371"
},
"total": 2456.078251134,
"count": 1,
"self": 0.4409478279999348,
"children": {
"run_training.setup": {
"total": 0.023845177999987754,
"count": 1,
"self": 0.023845177999987754
},
"TrainerController.start_learning": {
"total": 2455.613458128,
"count": 1,
"self": 4.710656520981047,
"children": {
"TrainerController._reset_env": {
"total": 3.4682679929999267,
"count": 1,
"self": 3.4682679929999267
},
"TrainerController.advance": {
"total": 2447.322224914019,
"count": 231138,
"self": 4.7118956510075805,
"children": {
"env_step": {
"total": 1973.5054675170059,
"count": 231138,
"self": 1551.871461930762,
"children": {
"SubprocessEnvManager._take_step": {
"total": 418.9631060051828,
"count": 231138,
"self": 16.334376606060232,
"children": {
"TorchPolicy.evaluate": {
"total": 402.62872939912256,
"count": 223098,
"self": 402.62872939912256
}
}
},
"workers": {
"total": 2.670899581060894,
"count": 231138,
"self": 0.0,
"children": {
"worker_root": {
"total": 2447.8760825221248,
"count": 231138,
"is_parallel": true,
"self": 1184.5598957111572,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009240269999963857,
"count": 1,
"is_parallel": true,
"self": 0.00025441699995099043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006696100000453953,
"count": 2,
"is_parallel": true,
"self": 0.0006696100000453953
}
}
},
"UnityEnvironment.step": {
"total": 0.0306293400000186,
"count": 1,
"is_parallel": true,
"self": 0.00031971300006716774,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001915919999646576,
"count": 1,
"is_parallel": true,
"self": 0.0001915919999646576
},
"communicator.exchange": {
"total": 0.029392637000000832,
"count": 1,
"is_parallel": true,
"self": 0.029392637000000832
},
"steps_from_proto": {
"total": 0.0007253979999859439,
"count": 1,
"is_parallel": true,
"self": 0.00018718799992711865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005382100000588252,
"count": 2,
"is_parallel": true,
"self": 0.0005382100000588252
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1263.3161868109676,
"count": 231137,
"is_parallel": true,
"self": 37.5220408488874,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.88298202696649,
"count": 231137,
"is_parallel": true,
"self": 79.88298202696649
},
"communicator.exchange": {
"total": 1057.4178019060978,
"count": 231137,
"is_parallel": true,
"self": 1057.4178019060978
},
"steps_from_proto": {
"total": 88.49336202901566,
"count": 231137,
"is_parallel": true,
"self": 30.746456379110782,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.746905649904875,
"count": 462274,
"is_parallel": true,
"self": 57.746905649904875
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.1048617460058,
"count": 231138,
"self": 7.289363199072227,
"children": {
"process_trajectory": {
"total": 157.13702471493298,
"count": 231138,
"self": 155.86200950493264,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2750152100003334,
"count": 10,
"self": 1.2750152100003334
}
}
},
"_update_policy": {
"total": 304.6784738320006,
"count": 96,
"self": 239.38434397199364,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.29412986000693,
"count": 2880,
"self": 65.29412986000693
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.239999260695186e-07,
"count": 1,
"self": 8.239999260695186e-07
},
"TrainerController._save_models": {
"total": 0.11230787599970427,
"count": 1,
"self": 0.001985413999591401,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11032246200011286,
"count": 1,
"self": 0.11032246200011286
}
}
}
}
}
}
}