mhea's picture
First Push
da78b57 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6129550933837891,
"min": 0.5848203301429749,
"max": 2.8594298362731934,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5825.525390625,
"min": 5777.72216796875,
"max": 29189.05859375,
"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": 12.944710731506348,
"min": 0.5839613080024719,
"max": 13.039704322814941,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.218505859375,
"min": 113.28849792480469,
"max": 2673.139404296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07162945462401052,
"min": 0.06127733584064259,
"max": 0.07507702128130797,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2865178184960421,
"min": 0.24510934336257037,
"max": 0.3753851064065398,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18351338610199153,
"min": 0.14321387230929938,
"max": 0.29771311500785397,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7340535444079661,
"min": 0.5728554892371975,
"max": 1.477071190289423,
"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": 25.75,
"min": 3.9545454545454546,
"max": 25.75,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 174.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.9545454545454546,
"max": 25.75,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 174.0,
"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": "1752645757",
"python_version": "3.10.12 (main, May 27 2025, 17:12:29) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752646305"
},
"total": 548.4568217460001,
"count": 1,
"self": 0.594992349999302,
"children": {
"run_training.setup": {
"total": 0.031834717000492674,
"count": 1,
"self": 0.031834717000492674
},
"TrainerController.start_learning": {
"total": 547.8299946790003,
"count": 1,
"self": 0.5914415259940142,
"children": {
"TrainerController._reset_env": {
"total": 3.997699431000001,
"count": 1,
"self": 3.997699431000001
},
"TrainerController.advance": {
"total": 543.167655300007,
"count": 18192,
"self": 0.6349064998239555,
"children": {
"env_step": {
"total": 382.2566055721036,
"count": 18192,
"self": 325.9280108050207,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.96761262202472,
"count": 18192,
"self": 1.8632613010586283,
"children": {
"TorchPolicy.evaluate": {
"total": 54.10435132096609,
"count": 18192,
"self": 54.10435132096609
}
}
},
"workers": {
"total": 0.3609821450581876,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 545.5669242110271,
"count": 18192,
"is_parallel": true,
"self": 262.97836515602467,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0062594790006187395,
"count": 1,
"is_parallel": true,
"self": 0.004571335000946419,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016881439996723202,
"count": 10,
"is_parallel": true,
"self": 0.0016881439996723202
}
}
},
"UnityEnvironment.step": {
"total": 0.04145742900072946,
"count": 1,
"is_parallel": true,
"self": 0.0006580800009032828,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004708030000983854,
"count": 1,
"is_parallel": true,
"self": 0.0004708030000983854
},
"communicator.exchange": {
"total": 0.03813669600003777,
"count": 1,
"is_parallel": true,
"self": 0.03813669600003777
},
"steps_from_proto": {
"total": 0.002191849999690021,
"count": 1,
"is_parallel": true,
"self": 0.0004519379990597372,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017399120006302837,
"count": 10,
"is_parallel": true,
"self": 0.0017399120006302837
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 282.5885590550024,
"count": 18191,
"is_parallel": true,
"self": 12.910992155052554,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.185545693004315,
"count": 18191,
"is_parallel": true,
"self": 7.185545693004315
},
"communicator.exchange": {
"total": 221.01344241297102,
"count": 18191,
"is_parallel": true,
"self": 221.01344241297102
},
"steps_from_proto": {
"total": 41.47857879397452,
"count": 18191,
"is_parallel": true,
"self": 7.979123474005064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.49945531996946,
"count": 181910,
"is_parallel": true,
"self": 33.49945531996946
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 160.2761432280795,
"count": 18192,
"self": 0.7526501670981816,
"children": {
"process_trajectory": {
"total": 29.98456322898346,
"count": 18192,
"self": 29.612332716984383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.37223051199907786,
"count": 4,
"self": 0.37223051199907786
}
}
},
"_update_policy": {
"total": 129.53892983199785,
"count": 90,
"self": 48.23653105300946,
"children": {
"TorchPPOOptimizer.update": {
"total": 81.30239877898839,
"count": 4587,
"self": 81.30239877898839
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0349995136493817e-06,
"count": 1,
"self": 1.0349995136493817e-06
},
"TrainerController._save_models": {
"total": 0.07319738699970912,
"count": 1,
"self": 0.0011012989998562261,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0720960879998529,
"count": 1,
"self": 0.0720960879998529
}
}
}
}
}
}
}