Vlack-Fangy's picture
First Push
399c006 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6597203016281128,
"min": 0.6556880474090576,
"max": 1.448788046836853,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 19897.1640625,
"min": 19481.802734375,
"max": 43950.43359375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989891.0,
"min": 29952.0,
"max": 989891.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989891.0,
"min": 29952.0,
"max": 989891.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.355521559715271,
"min": -0.11315317451953888,
"max": 0.3854027986526489,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 93.50216674804688,
"min": -27.383068084716797,
"max": 101.746337890625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0023667437490075827,
"min": -0.0003634938329923898,
"max": 0.5010976791381836,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.6224536299705505,
"min": -0.08941948413848877,
"max": 118.76014709472656,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06962900648885878,
"min": 0.0656452387765007,
"max": 0.07153748336713761,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9051770843551642,
"min": 0.4920234248783418,
"max": 1.0680203218653332,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012579718327312224,
"min": 0.00030620839538992434,
"max": 0.014242109039332719,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16353633825505892,
"min": 0.003980709140069016,
"max": 0.2136316355899908,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.538543641030768e-06,
"min": 7.538543641030768e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 9.800106733339998e-05,
"min": 9.800106733339998e-05,
"max": 0.0035079020306993994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251281538461539,
"min": 0.10251281538461539,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3326666,
"min": 1.3326666,
"max": 2.5693006000000005,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026103025692307693,
"min": 0.00026103025692307693,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00339339334,
"min": 0.00339339334,
"max": 0.11695312994000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012997359968721867,
"min": 0.012997359968721867,
"max": 0.5145584344863892,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.168965682387352,
"min": 0.168965682387352,
"max": 3.6019089221954346,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 481.37931034482756,
"min": 461.327868852459,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27920.0,
"min": 15984.0,
"max": 33207.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3116827339961612,
"min": -1.0000000521540642,
"max": 1.3746753879746452,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 76.07759857177734,
"min": -30.615801714360714,
"max": 86.85039889067411,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3116827339961612,
"min": -1.0000000521540642,
"max": 1.3746753879746452,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 76.07759857177734,
"min": -30.615801714360714,
"max": 86.85039889067411,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06441685953052065,
"min": 0.06441685953052065,
"max": 10.77686236333102,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.736177852770197,
"min": 3.736177852770197,
"max": 172.42979781329632,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1769277994",
"python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]",
"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",
"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": "1769281152"
},
"total": 3157.1723285470002,
"count": 1,
"self": 0.6351331519995256,
"children": {
"run_training.setup": {
"total": 0.046541255000192905,
"count": 1,
"self": 0.046541255000192905
},
"TrainerController.start_learning": {
"total": 3156.4906541400005,
"count": 1,
"self": 2.3046193200557354,
"children": {
"TrainerController._reset_env": {
"total": 3.304718350999792,
"count": 1,
"self": 3.304718350999792
},
"TrainerController.advance": {
"total": 3150.8176060249457,
"count": 63377,
"self": 2.494268313822431,
"children": {
"env_step": {
"total": 2116.030340733169,
"count": 63377,
"self": 1955.306300439247,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.29736527597106,
"count": 63377,
"self": 7.259096788965053,
"children": {
"TorchPolicy.evaluate": {
"total": 152.038268487006,
"count": 62559,
"self": 152.038268487006
}
}
},
"workers": {
"total": 1.4266750179508563,
"count": 63377,
"self": 0.0,
"children": {
"worker_root": {
"total": 3147.8323598831466,
"count": 63377,
"is_parallel": true,
"self": 1379.0853611771086,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004642269000214583,
"count": 1,
"is_parallel": true,
"self": 0.001710620000721974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029316489994926087,
"count": 8,
"is_parallel": true,
"self": 0.0029316489994926087
}
}
},
"UnityEnvironment.step": {
"total": 0.12582617600037338,
"count": 1,
"is_parallel": true,
"self": 0.0027185440003449912,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005025020000175573,
"count": 1,
"is_parallel": true,
"self": 0.0005025020000175573
},
"communicator.exchange": {
"total": 0.11776233399996272,
"count": 1,
"is_parallel": true,
"self": 0.11776233399996272
},
"steps_from_proto": {
"total": 0.004842796000048111,
"count": 1,
"is_parallel": true,
"self": 0.0004866400013270322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0043561559987210785,
"count": 8,
"is_parallel": true,
"self": 0.0043561559987210785
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1768.746998706038,
"count": 63376,
"is_parallel": true,
"self": 47.3560436010639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 31.644092426146926,
"count": 63376,
"is_parallel": true,
"self": 31.644092426146926
},
"communicator.exchange": {
"total": 1539.6504997679249,
"count": 63376,
"is_parallel": true,
"self": 1539.6504997679249
},
"steps_from_proto": {
"total": 150.09636291090237,
"count": 63376,
"is_parallel": true,
"self": 30.539128635611632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 119.55723427529074,
"count": 507008,
"is_parallel": true,
"self": 119.55723427529074
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1032.2929969779543,
"count": 63377,
"self": 4.444000635953671,
"children": {
"process_trajectory": {
"total": 161.24797797498968,
"count": 63377,
"self": 161.00076365398945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24721432100022867,
"count": 2,
"self": 0.24721432100022867
}
}
},
"_update_policy": {
"total": 866.601018367011,
"count": 446,
"self": 350.35726807407036,
"children": {
"TorchPPOOptimizer.update": {
"total": 516.2437502929406,
"count": 22791,
"self": 516.2437502929406
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1199999789823778e-06,
"count": 1,
"self": 1.1199999789823778e-06
},
"TrainerController._save_models": {
"total": 0.06370932399931917,
"count": 1,
"self": 0.0017163799993795692,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0619929439999396,
"count": 1,
"self": 0.0619929439999396
}
}
}
}
}
}
}