eswat's picture
Initial commit
5574070
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6743193864822388,
"min": 0.6618881821632385,
"max": 1.5247089862823486,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 20229.58203125,
"min": 19867.236328125,
"max": 46253.5703125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989897.0,
"min": 29952.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989897.0,
"min": 29952.0,
"max": 989897.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4287475049495697,
"min": -0.10496557503938675,
"max": 0.4287475049495697,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 117.04806518554688,
"min": -25.296703338623047,
"max": 117.04806518554688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.10881229490041733,
"min": -0.04274127259850502,
"max": 0.16199654340744019,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 29.70575714111328,
"min": -11.155471801757812,
"max": 38.39318084716797,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06868303824699233,
"min": 0.06376882453999952,
"max": 0.0734735924574639,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9615625354578927,
"min": 0.5112470934264851,
"max": 1.0781795774528289,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017300266743262127,
"min": 0.00022286790493757628,
"max": 0.017300266743262127,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24220373440566978,
"min": 0.002451546954313339,
"max": 0.24220373440566978,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.739433134507144e-06,
"min": 7.739433134507144e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010835206388310002,
"min": 0.00010835206388310002,
"max": 0.0031171789609404,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025797785714286,
"min": 0.1025797785714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4361169000000003,
"min": 1.3886848,
"max": 2.3591379000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026771987928571436,
"min": 0.00026771987928571436,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003748078310000001,
"min": 0.003748078310000001,
"max": 0.10392205404000002,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00789307989180088,
"min": 0.007817096076905727,
"max": 0.25898781418800354,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11050312221050262,
"min": 0.10943934321403503,
"max": 1.8129147291183472,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 420.75342465753425,
"min": 420.75342465753425,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30715.0,
"min": 15984.0,
"max": 33718.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.442216418683529,
"min": -1.0000000521540642,
"max": 1.5738610881898139,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 105.28179856389761,
"min": -32.000001668930054,
"max": 113.3179983496666,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.442216418683529,
"min": -1.0000000521540642,
"max": 1.5738610881898139,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 105.28179856389761,
"min": -32.000001668930054,
"max": 113.3179983496666,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.034424205383601636,
"min": 0.034424205383601636,
"max": 5.072410341352224,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.5129669930029195,
"min": 2.399562357692048,
"max": 81.15856546163559,
"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": "1680682264",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680684426"
},
"total": 2162.006944713,
"count": 1,
"self": 0.5381168780004373,
"children": {
"run_training.setup": {
"total": 0.12488311199990676,
"count": 1,
"self": 0.12488311199990676
},
"TrainerController.start_learning": {
"total": 2161.343944723,
"count": 1,
"self": 1.5641093220056064,
"children": {
"TrainerController._reset_env": {
"total": 3.919846319000044,
"count": 1,
"self": 3.919846319000044
},
"TrainerController.advance": {
"total": 2155.762804101994,
"count": 63380,
"self": 1.5884997020079936,
"children": {
"env_step": {
"total": 1523.4534143399278,
"count": 63380,
"self": 1406.1099226839883,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.38651586696596,
"count": 63380,
"self": 5.248307563933622,
"children": {
"TorchPolicy.evaluate": {
"total": 111.13820830303234,
"count": 62562,
"self": 111.13820830303234
}
}
},
"workers": {
"total": 0.9569757889735229,
"count": 63380,
"self": 0.0,
"children": {
"worker_root": {
"total": 2155.92539603199,
"count": 63380,
"is_parallel": true,
"self": 871.6160186730426,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018694259999847418,
"count": 1,
"is_parallel": true,
"self": 0.0005801190002330259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001289306999751716,
"count": 8,
"is_parallel": true,
"self": 0.001289306999751716
}
}
},
"UnityEnvironment.step": {
"total": 0.05861965200006125,
"count": 1,
"is_parallel": true,
"self": 0.0005899610000597022,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005351240001800761,
"count": 1,
"is_parallel": true,
"self": 0.0005351240001800761
},
"communicator.exchange": {
"total": 0.05567055400001664,
"count": 1,
"is_parallel": true,
"self": 0.05567055400001664
},
"steps_from_proto": {
"total": 0.001824012999804836,
"count": 1,
"is_parallel": true,
"self": 0.00041301399983240117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014109989999724348,
"count": 8,
"is_parallel": true,
"self": 0.0014109989999724348
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1284.3093773589476,
"count": 63379,
"is_parallel": true,
"self": 34.545682890877515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.96863397200218,
"count": 63379,
"is_parallel": true,
"self": 25.96863397200218
},
"communicator.exchange": {
"total": 1120.0125660190133,
"count": 63379,
"is_parallel": true,
"self": 1120.0125660190133
},
"steps_from_proto": {
"total": 103.78249447705457,
"count": 63379,
"is_parallel": true,
"self": 22.500224311894954,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.28227016515962,
"count": 507032,
"is_parallel": true,
"self": 81.28227016515962
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 630.7208900600583,
"count": 63380,
"self": 2.8182513450515216,
"children": {
"process_trajectory": {
"total": 113.59099282400689,
"count": 63380,
"self": 113.32237475700663,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26861806700026136,
"count": 2,
"self": 0.26861806700026136
}
}
},
"_update_policy": {
"total": 514.3116458909999,
"count": 434,
"self": 329.9683614760097,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.3432844149902,
"count": 22866,
"self": 184.3432844149902
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.09718395200025043,
"count": 1,
"self": 0.0021030960001553467,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09508085600009508,
"count": 1,
"self": 0.09508085600009508
}
}
}
}
}
}
}