PinchuPanda's picture
First Push
96ec9c6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0191810131072998,
"min": 1.0125811100006104,
"max": 2.8851497173309326,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9820.828125,
"min": 8866.5263671875,
"max": 41352.8515625,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.220526695251465,
"min": 0.41513773798942566,
"max": 14.232309341430664,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1393.611572265625,
"min": 40.26836013793945,
"max": 1494.2806396484375,
"count": 100
},
"SnowballTarget.Policy.CuriosityValueEstimate.mean": {
"value": 0.04185193032026291,
"min": -0.29990190267562866,
"max": 0.06766362488269806,
"count": 100
},
"SnowballTarget.Policy.CuriosityValueEstimate.sum": {
"value": 4.101489067077637,
"min": -29.090484619140625,
"max": 6.643495082855225,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 13134.0,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.622222222222224,
"min": 3.022727272727273,
"max": 28.295454545454547,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1243.0,
"min": 133.0,
"max": 1697.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.622222222222224,
"min": 3.022727272727273,
"max": 28.295454545454547,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1243.0,
"min": 133.0,
"max": 1697.0,
"count": 100
},
"SnowballTarget.Policy.CuriosityReward.mean": {
"value": 0.08641067225899961,
"min": 0.0,
"max": 0.29597962292080576,
"count": 100
},
"SnowballTarget.Policy.CuriosityReward.sum": {
"value": 3.8884802516549826,
"min": 0.0,
"max": 13.023103408515453,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.13800820862084176,
"min": 0.10502773270744717,
"max": 0.2210215118389125,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13800820862084176,
"min": 0.10502773270744717,
"max": 0.4027854288067443,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.08755119573889357,
"min": 0.06235209942767114,
"max": 0.1533522138541395,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.08755119573889357,
"min": 0.06235209942767114,
"max": 0.30033070142522,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.4952995015999965e-06,
"min": 1.4952995015999965e-06,
"max": 0.00029736000087999994,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.4952995015999965e-06,
"min": 1.4952995015999965e-06,
"max": 0.0005551200149599999,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1004984,
"min": 0.1004984,
"max": 0.19912000000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.1004984,
"min": 0.1004984,
"max": 0.38504000000000005,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.487015999999995e-05,
"min": 3.487015999999995e-05,
"max": 0.004956088,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 3.487015999999995e-05,
"min": 3.487015999999995e-05,
"max": 0.009253496,
"count": 100
},
"SnowballTarget.Losses.CuriosityForwardLoss.mean": {
"value": 0.0420269084473451,
"min": 0.04060459949753501,
"max": 0.3548051611040578,
"count": 100
},
"SnowballTarget.Losses.CuriosityForwardLoss.sum": {
"value": 0.0420269084473451,
"min": 0.04060459949753501,
"max": 0.3548051611040578,
"count": 100
},
"SnowballTarget.Losses.CuriosityInverseLoss.mean": {
"value": 0.8903695670041171,
"min": 0.8837436121521574,
"max": 2.870172796827374,
"count": 100
},
"SnowballTarget.Losses.CuriosityInverseLoss.sum": {
"value": 0.8903695670041171,
"min": 0.8903695670041171,
"max": 4.892745487617724,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1768629609",
"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=SnowballTarget_v2 --no-graphics --num-envs=4 --force",
"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": "1768630491"
},
"total": 881.6892560720444,
"count": 1,
"self": 0.5809017717838287,
"children": {
"run_training.setup": {
"total": 0.08153192698955536,
"count": 1,
"self": 0.08153192698955536
},
"TrainerController.start_learning": {
"total": 881.026822373271,
"count": 1,
"self": 1.2454327493906021,
"children": {
"TrainerController._reset_env": {
"total": 4.511491026729345,
"count": 1,
"self": 4.511491026729345
},
"TrainerController.advance": {
"total": 874.9155791327357,
"count": 85836,
"self": 1.1708364188671112,
"children": {
"env_step": {
"total": 498.63419465348125,
"count": 85836,
"self": 171.03251956030726,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.7886832021177,
"count": 91007,
"self": 4.9086459912359715,
"children": {
"TorchPolicy.evaluate": {
"total": 321.8800372108817,
"count": 91007,
"self": 321.8800372108817
}
}
},
"workers": {
"total": 0.8129918910562992,
"count": 85836,
"self": 0.0,
"children": {
"worker_root": {
"total": 3516.008899267763,
"count": 91004,
"is_parallel": true,
"self": 2077.2471702061594,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.013634655624628067,
"count": 4,
"is_parallel": true,
"self": 0.0038620606064796448,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.009772595018148422,
"count": 40,
"is_parallel": true,
"self": 0.009772595018148422
}
}
},
"UnityEnvironment.step": {
"total": 0.14024678990244865,
"count": 4,
"is_parallel": true,
"self": 0.003130599856376648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.001779858022928238,
"count": 4,
"is_parallel": true,
"self": 0.001779858022928238
},
"communicator.exchange": {
"total": 0.12624675035476685,
"count": 4,
"is_parallel": true,
"self": 0.12624675035476685
},
"steps_from_proto": {
"total": 0.009089581668376923,
"count": 4,
"is_parallel": true,
"self": 0.0016513243317604065,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.007438257336616516,
"count": 40,
"is_parallel": true,
"self": 0.007438257336616516
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1438.7617290616035,
"count": 91000,
"is_parallel": true,
"self": 57.816723734140396,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.81670133769512,
"count": 91000,
"is_parallel": true,
"self": 31.81670133769512
},
"communicator.exchange": {
"total": 1182.3738483600318,
"count": 91000,
"is_parallel": true,
"self": 1182.3738483600318
},
"steps_from_proto": {
"total": 166.75445562973619,
"count": 91000,
"is_parallel": true,
"self": 29.058784492313862,
"children": {
"_process_rank_one_or_two_observation": {
"total": 137.69567113742232,
"count": 910000,
"is_parallel": true,
"self": 137.69567113742232
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 375.1105480603874,
"count": 85836,
"self": 1.6210341788828373,
"children": {
"process_trajectory": {
"total": 189.18001991137862,
"count": 85836,
"self": 181.35321673750877,
"children": {
"RLTrainer._checkpoint": {
"total": 7.826803173869848,
"count": 20,
"self": 7.826803173869848
}
}
},
"_update_policy": {
"total": 184.3094939701259,
"count": 113,
"self": 88.27203316241503,
"children": {
"TorchPPOOptimizer.update": {
"total": 96.03746080771089,
"count": 3729,
"self": 96.03746080771089
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.92903995513916e-07,
"count": 1,
"self": 6.92903995513916e-07
},
"TrainerController._save_models": {
"total": 0.3543187715113163,
"count": 1,
"self": 0.026383914053440094,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3279348574578762,
"count": 1,
"self": 0.3279348574578762
}
}
}
}
}
}
}