Cryxim's picture
Initial
52777c2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.4636890888214111,
"min": 1.4636890888214111,
"max": 2.867575168609619,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7374.0654296875,
"min": 7047.1455078125,
"max": 14919.9931640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 4976.0,
"max": 99960.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 4976.0,
"max": 99960.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 9.67303466796875,
"min": 0.18131832778453827,
"max": 9.67303466796875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 938.2843627929688,
"min": 17.58787727355957,
"max": 1021.30810546875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06802103939173999,
"min": 0.055840596003762066,
"max": 0.08697465377737863,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13604207878347999,
"min": 0.11168119200752413,
"max": 0.20124649133661066,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2883444767372281,
"min": 0.11762858616809051,
"max": 0.4114743476989222,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5766889534744561,
"min": 0.23525717233618101,
"max": 1.1132753283954133,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.752097812000007e-06,
"min": 8.752097812000007e-06,
"max": 0.000387152003212,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.7504195624000015e-05,
"min": 1.7504195624000015e-05,
"max": 0.0009898560525360002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.103282,
"min": 0.103282,
"max": 0.24518199999999998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.206564,
"min": 0.206564,
"max": 0.671196,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 7.542120000000004e-05,
"min": 7.542120000000004e-05,
"max": 0.0029039611999999997,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00015084240000000007,
"min": 0.00015084240000000007,
"max": 0.0074291736,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 19.227272727272727,
"min": 2.3181818181818183,
"max": 19.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 423.0,
"min": 51.0,
"max": 639.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 19.227272727272727,
"min": 2.3181818181818183,
"max": 19.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 423.0,
"min": 51.0,
"max": 639.0,
"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": "1724852738",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724853054"
},
"total": 316.201266404,
"count": 1,
"self": 0.5404161260000819,
"children": {
"run_training.setup": {
"total": 0.10934108599997217,
"count": 1,
"self": 0.10934108599997217
},
"TrainerController.start_learning": {
"total": 315.55150919199997,
"count": 1,
"self": 0.4813312819990756,
"children": {
"TrainerController._reset_env": {
"total": 3.2808848450000028,
"count": 1,
"self": 3.2808848450000028
},
"TrainerController.advance": {
"total": 311.6971239770008,
"count": 9130,
"self": 0.21477125499671956,
"children": {
"env_step": {
"total": 311.48235272200407,
"count": 9130,
"self": 239.0659320109968,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.1961798140054,
"count": 9130,
"self": 1.3507899740037033,
"children": {
"TorchPolicy.evaluate": {
"total": 70.8453898400017,
"count": 9130,
"self": 70.8453898400017
}
}
},
"workers": {
"total": 0.22024089700187233,
"count": 9130,
"self": 0.0,
"children": {
"worker_root": {
"total": 314.38596736300155,
"count": 9130,
"is_parallel": true,
"self": 148.84802818199518,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003523613000027126,
"count": 1,
"is_parallel": true,
"self": 0.000968930999931672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002554682000095454,
"count": 10,
"is_parallel": true,
"self": 0.002554682000095454
}
}
},
"UnityEnvironment.step": {
"total": 0.04417224199994507,
"count": 1,
"is_parallel": true,
"self": 0.0008895689999803835,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004479300000070907,
"count": 1,
"is_parallel": true,
"self": 0.0004479300000070907
},
"communicator.exchange": {
"total": 0.04027469599998312,
"count": 1,
"is_parallel": true,
"self": 0.04027469599998312
},
"steps_from_proto": {
"total": 0.0025600469999744746,
"count": 1,
"is_parallel": true,
"self": 0.0005012109999142922,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020588360000601824,
"count": 10,
"is_parallel": true,
"self": 0.0020588360000601824
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 165.53793918100638,
"count": 9129,
"is_parallel": true,
"self": 7.591949900004067,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.924671496997462,
"count": 9129,
"is_parallel": true,
"self": 3.924671496997462
},
"communicator.exchange": {
"total": 130.90550475100338,
"count": 9129,
"is_parallel": true,
"self": 130.90550475100338
},
"steps_from_proto": {
"total": 23.115813033001473,
"count": 9129,
"is_parallel": true,
"self": 4.7070759769994766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.408737056001996,
"count": 91290,
"is_parallel": true,
"self": 18.408737056001996
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0008130110001047797,
"count": 1,
"self": 0.0008130110001047797,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 308.4177554929863,
"count": 362997,
"is_parallel": true,
"self": 8.985391187978166,
"children": {
"process_trajectory": {
"total": 166.97533915400834,
"count": 362997,
"is_parallel": true,
"self": 166.21491658300846,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7604225709998786,
"count": 3,
"is_parallel": true,
"self": 0.7604225709998786
}
}
},
"_update_policy": {
"total": 132.4570251509998,
"count": 45,
"is_parallel": true,
"self": 37.17752080900107,
"children": {
"TorchPPOOptimizer.update": {
"total": 95.27950434199875,
"count": 2292,
"is_parallel": true,
"self": 95.27950434199875
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09135607700000037,
"count": 1,
"self": 0.0013707370000020092,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08998533999999836,
"count": 1,
"self": 0.08998533999999836
}
}
}
}
}
}
}