AndExpo's picture
First Push
e2c0ed9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9633253812789917,
"min": 0.9633253812789917,
"max": 2.8536462783813477,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9155.4443359375,
"min": 9155.4443359375,
"max": 29130.021484375,
"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": 12.85942554473877,
"min": 0.4778648018836975,
"max": 12.85942554473877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2507.587890625,
"min": 92.70577239990234,
"max": 2588.26953125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06865977189747854,
"min": 0.0599036832173428,
"max": 0.07494714233211662,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2746390875899142,
"min": 0.2396147328693712,
"max": 0.37123412063217487,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19987254885627942,
"min": 0.11503176871052598,
"max": 0.295712954200366,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7994901954251177,
"min": 0.4601270748421039,
"max": 1.3428920878499162,
"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": 25.727272727272727,
"min": 3.727272727272727,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 164.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.727272727272727,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 164.0,
"max": 1395.0,
"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": "1746789578",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746790043"
},
"total": 464.4565784509998,
"count": 1,
"self": 0.4383982309998373,
"children": {
"run_training.setup": {
"total": 0.032209218999923905,
"count": 1,
"self": 0.032209218999923905
},
"TrainerController.start_learning": {
"total": 463.98597100100005,
"count": 1,
"self": 0.37566745999379236,
"children": {
"TrainerController._reset_env": {
"total": 3.102669307000042,
"count": 1,
"self": 3.102669307000042
},
"TrainerController.advance": {
"total": 460.4211049130063,
"count": 18192,
"self": 0.405693203009605,
"children": {
"env_step": {
"total": 329.10991563098446,
"count": 18192,
"self": 250.47428017300786,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.39912837999827,
"count": 18192,
"self": 1.383331698995562,
"children": {
"TorchPolicy.evaluate": {
"total": 77.01579668100271,
"count": 18192,
"self": 77.01579668100271
}
}
},
"workers": {
"total": 0.23650707797833093,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 462.5326358529958,
"count": 18192,
"is_parallel": true,
"self": 242.7771261269786,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006788870000036695,
"count": 1,
"is_parallel": true,
"self": 0.005153547000190883,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016353229998458119,
"count": 10,
"is_parallel": true,
"self": 0.0016353229998458119
}
}
},
"UnityEnvironment.step": {
"total": 0.03571074399997087,
"count": 1,
"is_parallel": true,
"self": 0.0006078469998556102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004470620001484349,
"count": 1,
"is_parallel": true,
"self": 0.0004470620001484349
},
"communicator.exchange": {
"total": 0.03276572799995847,
"count": 1,
"is_parallel": true,
"self": 0.03276572799995847
},
"steps_from_proto": {
"total": 0.0018901070000083564,
"count": 1,
"is_parallel": true,
"self": 0.00045041399994261155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014396930000657449,
"count": 10,
"is_parallel": true,
"self": 0.0014396930000657449
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 219.75550972601718,
"count": 18191,
"is_parallel": true,
"self": 10.490143399012368,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.00069558298901,
"count": 18191,
"is_parallel": true,
"self": 6.00069558298901
},
"communicator.exchange": {
"total": 168.11781700499114,
"count": 18191,
"is_parallel": true,
"self": 168.11781700499114
},
"steps_from_proto": {
"total": 35.146853739024664,
"count": 18191,
"is_parallel": true,
"self": 6.347304646040811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.799549092983852,
"count": 181910,
"is_parallel": true,
"self": 28.799549092983852
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 130.9054960790122,
"count": 18192,
"self": 0.4367288500175164,
"children": {
"process_trajectory": {
"total": 30.545829936998416,
"count": 18192,
"self": 30.039128172998744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.506701763999672,
"count": 4,
"self": 0.506701763999672
}
}
},
"_update_policy": {
"total": 99.92293729199628,
"count": 90,
"self": 40.77808210700073,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.14485518499555,
"count": 4587,
"self": 59.14485518499555
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0999997357430402e-06,
"count": 1,
"self": 1.0999997357430402e-06
},
"TrainerController._save_models": {
"total": 0.08652822100020785,
"count": 1,
"self": 0.000759335000111605,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08576888600009624,
"count": 1,
"self": 0.08576888600009624
}
}
}
}
}
}
}