tstenborg's picture
First Push
d0c0330 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5542722344398499,
"min": 0.5542722344398499,
"max": 2.8838727474212646,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5316.5791015625,
"min": 5316.5791015625,
"max": 29438.57421875,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.13492488861084,
"min": 0.16611996293067932,
"max": 13.146997451782227,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2692.65966796875,
"min": 32.227272033691406,
"max": 2693.017578125,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.21818181818182,
"min": 3.022727272727273,
"max": 26.21818181818182,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1442.0,
"min": 133.0,
"max": 1442.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.21818181818182,
"min": 3.022727272727273,
"max": 26.21818181818182,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1442.0,
"min": 133.0,
"max": 1442.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.03147940009845721,
"min": 0.026314870278535334,
"max": 0.04353076896707837,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.06295880019691442,
"min": 0.05262974055707067,
"max": 0.10813349625095726,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21817268679539362,
"min": 0.10989613986263672,
"max": 0.314934233824412,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.43634537359078723,
"min": 0.21979227972527343,
"max": 0.934617462257544,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.5440989824000048e-06,
"min": 2.5440989824000048e-06,
"max": 0.0002467440013024,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.0881979648000096e-06,
"min": 5.0881979648000096e-06,
"max": 0.0006973320210672001,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1010176,
"min": 0.1010176,
"max": 0.19869760000000003,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.2020352,
"min": 0.2020352,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.07782400000001e-05,
"min": 6.07782400000001e-05,
"max": 0.00493501024,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001215564800000002,
"min": 0.0001215564800000002,
"max": 0.01394874672,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1758638096",
"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": "1758639074"
},
"total": 978.5725450599999,
"count": 1,
"self": 0.5358361889999514,
"children": {
"run_training.setup": {
"total": 0.026390196000079413,
"count": 1,
"self": 0.026390196000079413
},
"TrainerController.start_learning": {
"total": 978.0103186749999,
"count": 1,
"self": 0.8062527589886486,
"children": {
"TrainerController._reset_env": {
"total": 4.0399974360000215,
"count": 1,
"self": 4.0399974360000215
},
"TrainerController.advance": {
"total": 973.089120138011,
"count": 45464,
"self": 0.8840970980044176,
"children": {
"env_step": {
"total": 773.9588200109954,
"count": 45464,
"self": 604.7851077520024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 168.64965381700756,
"count": 45464,
"self": 3.05053589401291,
"children": {
"TorchPolicy.evaluate": {
"total": 165.59911792299465,
"count": 45464,
"self": 165.59911792299465
}
}
},
"workers": {
"total": 0.5240584419854031,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 973.483170302988,
"count": 45464,
"is_parallel": true,
"self": 441.2814674599756,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003797415999997611,
"count": 1,
"is_parallel": true,
"self": 0.00176412600023923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002033289999758381,
"count": 10,
"is_parallel": true,
"self": 0.002033289999758381
}
}
},
"UnityEnvironment.step": {
"total": 0.03463948599994637,
"count": 1,
"is_parallel": true,
"self": 0.0005781659999684052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040957700002763886,
"count": 1,
"is_parallel": true,
"self": 0.00040957700002763886
},
"communicator.exchange": {
"total": 0.031797998000001826,
"count": 1,
"is_parallel": true,
"self": 0.031797998000001826
},
"steps_from_proto": {
"total": 0.0018537449999485034,
"count": 1,
"is_parallel": true,
"self": 0.00034820100006527355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015055439998832298,
"count": 10,
"is_parallel": true,
"self": 0.0015055439998832298
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 532.2017028430124,
"count": 45463,
"is_parallel": true,
"self": 25.25465786800521,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.095877366000536,
"count": 45463,
"is_parallel": true,
"self": 13.095877366000536
},
"communicator.exchange": {
"total": 405.8851357060147,
"count": 45463,
"is_parallel": true,
"self": 405.8851357060147
},
"steps_from_proto": {
"total": 87.96603190299197,
"count": 45463,
"is_parallel": true,
"self": 16.204365830076313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.76166607291566,
"count": 454630,
"is_parallel": true,
"self": 71.76166607291566
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 198.2462030290112,
"count": 45464,
"self": 1.0330402599760191,
"children": {
"process_trajectory": {
"total": 65.41069691703615,
"count": 45464,
"self": 64.47495418303652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.935742733999632,
"count": 10,
"self": 0.935742733999632
}
}
},
"_update_policy": {
"total": 131.80246585199905,
"count": 113,
"self": 91.77342432499108,
"children": {
"TorchPPOOptimizer.update": {
"total": 40.02904152700796,
"count": 2712,
"self": 40.02904152700796
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.750000688451109e-07,
"count": 1,
"self": 8.750000688451109e-07
},
"TrainerController._save_models": {
"total": 0.07494746700012911,
"count": 1,
"self": 0.0009105369999815593,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07403693000014755,
"count": 1,
"self": 0.07403693000014755
}
}
}
}
}
}
}