sun-s's picture
First Push
1ff1b45 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.23002314567565918,
"min": 0.23002314567565918,
"max": 0.2349260151386261,
"count": 2
},
"Pyramids.Policy.Entropy.sum": {
"value": 6878.6123046875,
"min": 962.2569580078125,
"max": 6878.6123046875,
"count": 2
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 256.3893805309734,
"min": 161.07692307692307,
"max": 256.3893805309734,
"count": 2
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28972.0,
"min": 2094.0,
"max": 28972.0,
"count": 2
},
"Pyramids.Step.mean": {
"value": 1799881.0,
"min": 1769900.0,
"max": 1799881.0,
"count": 2
},
"Pyramids.Step.sum": {
"value": 1799881.0,
"min": 1769900.0,
"max": 1799881.0,
"count": 2
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7569994926452637,
"min": 0.678454577922821,
"max": 0.7569994926452637,
"count": 2
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 227.099853515625,
"min": 19.675182342529297,
"max": 227.099853515625,
"count": 2
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.012088575400412083,
"min": 0.008476777002215385,
"max": 0.012088575400412083,
"count": 2
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.626572608947754,
"min": 0.24582652747631073,
"max": 3.626572608947754,
"count": 2
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6904991007352297,
"min": 1.6904991007352297,
"max": 1.8389230691469634,
"count": 2
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 191.02639838308096,
"min": 23.905999898910522,
"max": 191.02639838308096,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6904991007352297,
"min": 1.6904991007352297,
"max": 1.8389230691469634,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 191.02639838308096,
"min": 23.905999898910522,
"max": 191.02639838308096,
"count": 2
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.018811457589605052,
"min": 0.01282379139537135,
"max": 0.018811457589605052,
"count": 2
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.125694707625371,
"min": 0.16670928813982755,
"max": 2.125694707625371,
"count": 2
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06903989427103494,
"min": 0.06903989427103494,
"max": 0.07371086557395756,
"count": 2
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9665585197944891,
"min": 0.07371086557395756,
"max": 0.9665585197944891,
"count": 2
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013754324653529604,
"min": 0.012180158829626938,
"max": 0.013754324653529604,
"count": 2
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19256054514941445,
"min": 0.012180158829626938,
"max": 0.19256054514941445,
"count": 2
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.579956282904759e-06,
"min": 2.579956282904759e-06,
"max": 5.192598269166678e-06,
"count": 2
},
"Pyramids.Policy.LearningRate.sum": {
"value": 3.611938796066663e-05,
"min": 5.192598269166678e-06,
"max": 3.611938796066663e-05,
"count": 2
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10085995238095238,
"min": 0.10085995238095238,
"max": 0.10173083333333334,
"count": 2
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4120393333333334,
"min": 0.10173083333333334,
"max": 1.4120393333333334,
"count": 2
},
"Pyramids.Policy.Beta.mean": {
"value": 9.590924285714278e-05,
"min": 9.590924285714278e-05,
"max": 0.00018291025000000038,
"count": 2
},
"Pyramids.Policy.Beta.sum": {
"value": 0.001342729399999999,
"min": 0.00018291025000000038,
"max": 0.001342729399999999,
"count": 2
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007161482237279415,
"min": 0.007161482237279415,
"max": 0.00789132621139288,
"count": 2
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.10026074945926666,
"min": 0.00789132621139288,
"max": 0.10026074945926666,
"count": 2
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1731251188",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1731251323"
},
"total": 135.19815375500002,
"count": 1,
"self": 0.5859790390004491,
"children": {
"run_training.setup": {
"total": 0.07201316099963151,
"count": 1,
"self": 0.07201316099963151
},
"TrainerController.start_learning": {
"total": 134.54016155499994,
"count": 1,
"self": 0.09100989502803714,
"children": {
"TrainerController._reset_env": {
"total": 2.9381275530013227,
"count": 1,
"self": 2.9381275530013227
},
"TrainerController.advance": {
"total": 131.385036688971,
"count": 2225,
"self": 0.09723937104718061,
"children": {
"env_step": {
"total": 94.80059798196453,
"count": 2225,
"self": 89.0568305868619,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5.693836227041174,
"count": 2225,
"self": 0.25347547404817306,
"children": {
"TorchPolicy.evaluate": {
"total": 5.440360752993001,
"count": 2125,
"self": 5.440360752993001
}
}
},
"workers": {
"total": 0.04993116806144826,
"count": 2225,
"self": 0.0,
"children": {
"worker_root": {
"total": 134.133400489025,
"count": 2225,
"is_parallel": true,
"self": 51.57458433508509,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003390834999663639,
"count": 1,
"is_parallel": true,
"self": 0.0012023240014968906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021885109981667483,
"count": 8,
"is_parallel": true,
"self": 0.0021885109981667483
}
}
},
"UnityEnvironment.step": {
"total": 0.06320548599978792,
"count": 1,
"is_parallel": true,
"self": 0.0007980729988048552,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005841059992235387,
"count": 1,
"is_parallel": true,
"self": 0.0005841059992235387
},
"communicator.exchange": {
"total": 0.059672103001503274,
"count": 1,
"is_parallel": true,
"self": 0.059672103001503274
},
"steps_from_proto": {
"total": 0.002151204000256257,
"count": 1,
"is_parallel": true,
"self": 0.0004450900014489889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017061139988072682,
"count": 8,
"is_parallel": true,
"self": 0.0017061139988072682
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 82.55881615393992,
"count": 2224,
"is_parallel": true,
"self": 1.817727706860751,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.0687961510229798,
"count": 2224,
"is_parallel": true,
"self": 1.0687961510229798
},
"communicator.exchange": {
"total": 74.94538597800783,
"count": 2224,
"is_parallel": true,
"self": 74.94538597800783
},
"steps_from_proto": {
"total": 4.72690631804835,
"count": 2224,
"is_parallel": true,
"self": 1.049798340005509,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.677107978042841,
"count": 17792,
"is_parallel": true,
"self": 3.677107978042841
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 36.4871993359593,
"count": 2225,
"self": 0.17099180796503788,
"children": {
"process_trajectory": {
"total": 6.615834170994276,
"count": 2225,
"self": 6.615834170994276
},
"_update_policy": {
"total": 29.70037335699999,
"count": 15,
"self": 11.611023433999435,
"children": {
"TorchPPOOptimizer.update": {
"total": 18.089349923000555,
"count": 720,
"self": 18.089349923000555
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0980002116411924e-06,
"count": 1,
"self": 1.0980002116411924e-06
},
"TrainerController._save_models": {
"total": 0.12598631999935606,
"count": 1,
"self": 0.0025059139989025425,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12348040600045351,
"count": 1,
"self": 0.12348040600045351
}
}
}
}
}
}
}