aselbaekki's picture
First Push
279a843 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7768747806549072,
"min": 0.7768747806549072,
"max": 2.85566782951355,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7383.41796875,
"min": 7383.41796875,
"max": 29150.658203125,
"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": 12.984009742736816,
"min": 0.395048588514328,
"max": 12.984009742736816,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2531.8818359375,
"min": 76.6394271850586,
"max": 2598.7724609375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07048783071841885,
"min": 0.06400187278660607,
"max": 0.07393778698957142,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2819513228736754,
"min": 0.2560074911464243,
"max": 0.363262240463918,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20519853664525584,
"min": 0.12383576917608141,
"max": 0.2769847786894032,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8207941465810233,
"min": 0.49534307670432565,
"max": 1.2964472288594528,
"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": 26.272727272727273,
"min": 3.3181818181818183,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1156.0,
"min": 146.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.272727272727273,
"min": 3.3181818181818183,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1156.0,
"min": 146.0,
"max": 1406.0,
"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": "1739128534",
"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 --force",
"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": "1739129008"
},
"total": 474.03710926099984,
"count": 1,
"self": 0.47512613200001397,
"children": {
"run_training.setup": {
"total": 0.021771711999917898,
"count": 1,
"self": 0.021771711999917898
},
"TrainerController.start_learning": {
"total": 473.5402114169999,
"count": 1,
"self": 0.43901422101203025,
"children": {
"TrainerController._reset_env": {
"total": 2.0779925440001534,
"count": 1,
"self": 2.0779925440001534
},
"TrainerController.advance": {
"total": 470.9276287249877,
"count": 18192,
"self": 0.4383110680118989,
"children": {
"env_step": {
"total": 337.7193548469834,
"count": 18192,
"self": 256.56453085199973,
"children": {
"SubprocessEnvManager._take_step": {
"total": 80.91041039897823,
"count": 18192,
"self": 1.4272516189701037,
"children": {
"TorchPolicy.evaluate": {
"total": 79.48315878000813,
"count": 18192,
"self": 79.48315878000813
}
}
},
"workers": {
"total": 0.24441359600541546,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 471.7703449249975,
"count": 18192,
"is_parallel": true,
"self": 247.76255142702257,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025784229999317176,
"count": 1,
"is_parallel": true,
"self": 0.0008050249998632353,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017733980000684824,
"count": 10,
"is_parallel": true,
"self": 0.0017733980000684824
}
}
},
"UnityEnvironment.step": {
"total": 0.03762570899993989,
"count": 1,
"is_parallel": true,
"self": 0.0005679839998720126,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039969499994185753,
"count": 1,
"is_parallel": true,
"self": 0.00039969499994185753
},
"communicator.exchange": {
"total": 0.03460477700014053,
"count": 1,
"is_parallel": true,
"self": 0.03460477700014053
},
"steps_from_proto": {
"total": 0.0020532529999854887,
"count": 1,
"is_parallel": true,
"self": 0.0004177630007689004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016354899992165883,
"count": 10,
"is_parallel": true,
"self": 0.0016354899992165883
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 224.00779349797494,
"count": 18191,
"is_parallel": true,
"self": 10.308079021980575,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8888965000023745,
"count": 18191,
"is_parallel": true,
"self": 5.8888965000023745
},
"communicator.exchange": {
"total": 172.81055073498965,
"count": 18191,
"is_parallel": true,
"self": 172.81055073498965
},
"steps_from_proto": {
"total": 35.00026724100235,
"count": 18191,
"is_parallel": true,
"self": 6.422014625949259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.57825261505309,
"count": 181910,
"is_parallel": true,
"self": 28.57825261505309
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 132.76996280999242,
"count": 18192,
"self": 0.4884190920092806,
"children": {
"process_trajectory": {
"total": 29.9698849659826,
"count": 18192,
"self": 29.401676827982783,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5682081379998181,
"count": 4,
"self": 0.5682081379998181
}
}
},
"_update_policy": {
"total": 102.31165875200054,
"count": 90,
"self": 41.61796221800273,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.69369653399781,
"count": 4587,
"self": 60.69369653399781
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2450000212993473e-06,
"count": 1,
"self": 1.2450000212993473e-06
},
"TrainerController._save_models": {
"total": 0.09557468200000585,
"count": 1,
"self": 0.002133183000069039,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09344149899993681,
"count": 1,
"self": 0.09344149899993681
}
}
}
}
}
}
}