hudaifah's picture
First training of SnowballTarget
4f0c1a4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.819433331489563,
"min": 0.819433331489563,
"max": 2.8639328479766846,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7787.89453125,
"min": 7787.89453125,
"max": 29235.02734375,
"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": 12.569111824035645,
"min": 0.48455551266670227,
"max": 12.569111824035645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2450.976806640625,
"min": 94.00376892089844,
"max": 2555.540283203125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0684901649864532,
"min": 0.06206120692950208,
"max": 0.07362825086684989,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2739606599458128,
"min": 0.2622591934332912,
"max": 0.36814125433424943,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16306905941489866,
"min": 0.10857262448453363,
"max": 0.23822932734208946,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6522762376595946,
"min": 0.4342904979381345,
"max": 1.1911466367104473,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.0776097306000005e-05,
"min": 1.0776097306000005e-05,
"max": 0.000389176002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 4.310438922400002e-05,
"min": 4.310438922400002e-05,
"max": 0.0018468800382800002,
"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": 24.886363636363637,
"min": 3.6363636363636362,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 160.0,
"max": 1351.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.886363636363637,
"min": 3.6363636363636362,
"max": 24.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 160.0,
"max": 1351.0,
"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": "1742814836",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742815250"
},
"total": 414.10692094599995,
"count": 1,
"self": 0.43878374599967174,
"children": {
"run_training.setup": {
"total": 0.02448960700007774,
"count": 1,
"self": 0.02448960700007774
},
"TrainerController.start_learning": {
"total": 413.6436475930002,
"count": 1,
"self": 0.31381064098991374,
"children": {
"TrainerController._reset_env": {
"total": 3.2717760110001564,
"count": 1,
"self": 3.2717760110001564
},
"TrainerController.advance": {
"total": 409.9705081540101,
"count": 18192,
"self": 0.3649268259907785,
"children": {
"env_step": {
"total": 289.3026262539868,
"count": 18192,
"self": 219.75085802397598,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.36043646999883,
"count": 18192,
"self": 1.20702649198779,
"children": {
"TorchPolicy.evaluate": {
"total": 68.15340997801104,
"count": 18192,
"self": 68.15340997801104
}
}
},
"workers": {
"total": 0.19133176001196261,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.27534710399686,
"count": 18192,
"is_parallel": true,
"self": 219.3415546280121,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005693838999832224,
"count": 1,
"is_parallel": true,
"self": 0.004013976999658553,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016798620001736708,
"count": 10,
"is_parallel": true,
"self": 0.0016798620001736708
}
}
},
"UnityEnvironment.step": {
"total": 0.03409227900010592,
"count": 1,
"is_parallel": true,
"self": 0.0005928829998538276,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037566600008176465,
"count": 1,
"is_parallel": true,
"self": 0.00037566600008176465
},
"communicator.exchange": {
"total": 0.031327153000120234,
"count": 1,
"is_parallel": true,
"self": 0.031327153000120234
},
"steps_from_proto": {
"total": 0.0017965770000500925,
"count": 1,
"is_parallel": true,
"self": 0.0003462380002474674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001450338999802625,
"count": 10,
"is_parallel": true,
"self": 0.001450338999802625
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.93379247598477,
"count": 18191,
"is_parallel": true,
"self": 9.729909312993868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.2797886660011955,
"count": 18191,
"is_parallel": true,
"self": 5.2797886660011955
},
"communicator.exchange": {
"total": 147.5907545989985,
"count": 18191,
"is_parallel": true,
"self": 147.5907545989985
},
"steps_from_proto": {
"total": 30.33333989799121,
"count": 18191,
"is_parallel": true,
"self": 5.352487247936779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.98085265005443,
"count": 181910,
"is_parallel": true,
"self": 24.98085265005443
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 120.30295507403252,
"count": 18192,
"self": 0.3817603510308345,
"children": {
"process_trajectory": {
"total": 26.26562319700156,
"count": 18192,
"self": 25.785995438001464,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47962775900009547,
"count": 4,
"self": 0.47962775900009547
}
}
},
"_update_policy": {
"total": 93.65557152600013,
"count": 90,
"self": 36.88703203100431,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.76853949499582,
"count": 4587,
"self": 56.76853949499582
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.770000476943096e-07,
"count": 1,
"self": 8.770000476943096e-07
},
"TrainerController._save_models": {
"total": 0.08755191000000195,
"count": 1,
"self": 0.0009293890000208194,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08662252099998113,
"count": 1,
"self": 0.08662252099998113
}
}
}
}
}
}
}