Kayvun Nadi
First Push
e2f090f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7889832854270935,
"min": 0.7889832854270935,
"max": 2.83398699760437,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7498.4970703125,
"min": 7498.4970703125,
"max": 28929.33984375,
"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": 13.087367057800293,
"min": 0.3267550766468048,
"max": 13.087367057800293,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.03662109375,
"min": 63.39048767089844,
"max": 2659.5634765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06624187675198281,
"min": 0.06175078056493672,
"max": 0.07370735420137826,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26496750700793126,
"min": 0.24700312225974688,
"max": 0.3589714722035627,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1981783273684628,
"min": 0.07927250851507245,
"max": 0.27316759976686217,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7927133094738512,
"min": 0.3170900340602898,
"max": 1.3658379988343108,
"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": 25.5,
"min": 2.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 112.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 2.5454545454545454,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 112.0,
"max": 1429.0,
"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": "1764066846",
"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": "1764067263"
},
"total": 417.0548637569999,
"count": 1,
"self": 0.4368134569999711,
"children": {
"run_training.setup": {
"total": 0.027453315000002476,
"count": 1,
"self": 0.027453315000002476
},
"TrainerController.start_learning": {
"total": 416.59059698499993,
"count": 1,
"self": 0.3191511759965806,
"children": {
"TrainerController._reset_env": {
"total": 2.9637433580001016,
"count": 1,
"self": 2.9637433580001016
},
"TrainerController.advance": {
"total": 413.23577169100327,
"count": 18192,
"self": 0.3333148310116485,
"children": {
"env_step": {
"total": 297.0576853180004,
"count": 18192,
"self": 232.56777995501852,
"children": {
"SubprocessEnvManager._take_step": {
"total": 64.30373020899015,
"count": 18192,
"self": 1.1637820599921724,
"children": {
"TorchPolicy.evaluate": {
"total": 63.13994814899797,
"count": 18192,
"self": 63.13994814899797
}
}
},
"workers": {
"total": 0.18617515399171225,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 414.820680840004,
"count": 18192,
"is_parallel": true,
"self": 209.95857351900497,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005126541999970868,
"count": 1,
"is_parallel": true,
"self": 0.0035536479998654613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001572894000105407,
"count": 10,
"is_parallel": true,
"self": 0.001572894000105407
}
}
},
"UnityEnvironment.step": {
"total": 0.0355862790000856,
"count": 1,
"is_parallel": true,
"self": 0.0006946680000510241,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004781099999036087,
"count": 1,
"is_parallel": true,
"self": 0.0004781099999036087
},
"communicator.exchange": {
"total": 0.032627201000082096,
"count": 1,
"is_parallel": true,
"self": 0.032627201000082096
},
"steps_from_proto": {
"total": 0.0017863000000488682,
"count": 1,
"is_parallel": true,
"self": 0.00036397300016233203,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014223269998865362,
"count": 10,
"is_parallel": true,
"self": 0.0014223269998865362
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.86210732099903,
"count": 18191,
"is_parallel": true,
"self": 9.968406321973703,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.192610992006735,
"count": 18191,
"is_parallel": true,
"self": 5.192610992006735
},
"communicator.exchange": {
"total": 155.67279006700994,
"count": 18191,
"is_parallel": true,
"self": 155.67279006700994
},
"steps_from_proto": {
"total": 34.02829994000865,
"count": 18191,
"is_parallel": true,
"self": 6.215930065021553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.8123698749871,
"count": 181910,
"is_parallel": true,
"self": 27.8123698749871
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.84477154199124,
"count": 18192,
"self": 0.3874647359810979,
"children": {
"process_trajectory": {
"total": 25.18280235200905,
"count": 18192,
"self": 24.72200230500914,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46080004699990695,
"count": 4,
"self": 0.46080004699990695
}
}
},
"_update_policy": {
"total": 90.27450445400109,
"count": 90,
"self": 37.14494090901201,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.12956354498908,
"count": 4587,
"self": 53.12956354498908
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.81000005392707e-07,
"count": 1,
"self": 8.81000005392707e-07
},
"TrainerController._save_models": {
"total": 0.07192987899998116,
"count": 1,
"self": 0.000655739999956495,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07127413900002466,
"count": 1,
"self": 0.07127413900002466
}
}
}
}
}
}
}