pyramids-RND-1 / run_logs /timers.json
ahmad-alismail's picture
Training first pyramids model
7877f39
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.773804247379303,
"min": 0.7373262047767639,
"max": 1.4236122369766235,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 23276.03125,
"min": 22155.177734375,
"max": 43186.69921875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989904.0,
"min": 29999.0,
"max": 989904.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989904.0,
"min": 29999.0,
"max": 989904.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.20350484549999237,
"min": -0.10546757280826569,
"max": 0.20350484549999237,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 50.87621307373047,
"min": -25.41768455505371,
"max": 50.87621307373047,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.023578910157084465,
"min": 0.006640828214585781,
"max": 0.3396361172199249,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.89472770690918,
"min": 1.646925449371338,
"max": 80.8333969116211,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06941177419295336,
"min": 0.06579946868089177,
"max": 0.0726302859438093,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.971764838701347,
"min": 0.5043251165163759,
"max": 1.0385350607102737,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.008495031351707266,
"min": 0.00024763664138175535,
"max": 0.008824990439248285,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11893043892390173,
"min": 0.002971639696581064,
"max": 0.11893043892390173,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.444576089935718e-06,
"min": 7.444576089935718e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010422406525910005,
"min": 0.00010422406525910005,
"max": 0.0034371228542923993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248149285714285,
"min": 0.10248149285714285,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4347409,
"min": 1.3886848,
"max": 2.5277522000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002579011364285716,
"min": 0.0002579011364285716,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036106159100000026,
"min": 0.0036106159100000026,
"max": 0.11457618924,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009398612193763256,
"min": 0.009334072470664978,
"max": 0.3667783737182617,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13158057630062103,
"min": 0.1306770145893097,
"max": 2.567448616027832,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 736.8048780487804,
"min": 683.9047619047619,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30209.0,
"min": 16798.0,
"max": 32286.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.49484282785228323,
"min": -0.9999290844125133,
"max": 0.696871389235769,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 20.783398769795895,
"min": -31.997201666235924,
"max": 29.268598347902298,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.49484282785228323,
"min": -0.9999290844125133,
"max": 0.696871389235769,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 20.783398769795895,
"min": -31.997201666235924,
"max": 29.268598347902298,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07221311930611375,
"min": 0.07221311930611375,
"max": 6.997588478467044,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.0329510108567774,
"min": 3.0329510108567774,
"max": 118.95900413393974,
"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": "1675872095",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675874337"
},
"total": 2241.7112756509987,
"count": 1,
"self": 0.5327859779981736,
"children": {
"run_training.setup": {
"total": 0.10839621300056024,
"count": 1,
"self": 0.10839621300056024
},
"TrainerController.start_learning": {
"total": 2241.07009346,
"count": 1,
"self": 1.5263148231206287,
"children": {
"TrainerController._reset_env": {
"total": 7.318683310999404,
"count": 1,
"self": 7.318683310999404
},
"TrainerController.advance": {
"total": 2232.132163226882,
"count": 63287,
"self": 1.5277330167582477,
"children": {
"env_step": {
"total": 1483.3742665060263,
"count": 63287,
"self": 1361.4182872190731,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.99662796404391,
"count": 63287,
"self": 4.78359594205358,
"children": {
"TorchPolicy.evaluate": {
"total": 116.21303202199033,
"count": 62552,
"self": 38.82645211286672,
"children": {
"TorchPolicy.sample_actions": {
"total": 77.38657990912361,
"count": 62552,
"self": 77.38657990912361
}
}
}
}
},
"workers": {
"total": 0.9593513229092423,
"count": 63287,
"self": 0.0,
"children": {
"worker_root": {
"total": 2235.4048082548807,
"count": 63287,
"is_parallel": true,
"self": 996.0942807549727,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018165629999202793,
"count": 1,
"is_parallel": true,
"self": 0.0006708079999953043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001145754999924975,
"count": 8,
"is_parallel": true,
"self": 0.001145754999924975
}
}
},
"UnityEnvironment.step": {
"total": 0.04732044800039148,
"count": 1,
"is_parallel": true,
"self": 0.0006208300010257517,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004434219999893685,
"count": 1,
"is_parallel": true,
"self": 0.0004434219999893685
},
"communicator.exchange": {
"total": 0.044562368999322644,
"count": 1,
"is_parallel": true,
"self": 0.044562368999322644
},
"steps_from_proto": {
"total": 0.001693827000053716,
"count": 1,
"is_parallel": true,
"self": 0.00041952099945774535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012743060005959705,
"count": 8,
"is_parallel": true,
"self": 0.0012743060005959705
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1239.310527499908,
"count": 63286,
"is_parallel": true,
"self": 32.29475761897811,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.732910687986077,
"count": 63286,
"is_parallel": true,
"self": 23.732910687986077
},
"communicator.exchange": {
"total": 1078.4793845369286,
"count": 63286,
"is_parallel": true,
"self": 1078.4793845369286
},
"steps_from_proto": {
"total": 104.80347465601517,
"count": 63286,
"is_parallel": true,
"self": 23.489861158023814,
"children": {
"_process_rank_one_or_two_observation": {
"total": 81.31361349799135,
"count": 506288,
"is_parallel": true,
"self": 81.31361349799135
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 747.2301637040973,
"count": 63287,
"self": 2.9222136793232494,
"children": {
"process_trajectory": {
"total": 165.02389300377217,
"count": 63287,
"self": 164.8382325467719,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18566045700026734,
"count": 2,
"self": 0.18566045700026734
}
}
},
"_update_policy": {
"total": 579.2840570210019,
"count": 453,
"self": 224.85034261592045,
"children": {
"TorchPPOOptimizer.update": {
"total": 354.43371440508145,
"count": 22803,
"self": 354.43371440508145
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.669994713272899e-07,
"count": 1,
"self": 8.669994713272899e-07
},
"TrainerController._save_models": {
"total": 0.0929312319985911,
"count": 1,
"self": 0.0014127260001259856,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09151850599846512,
"count": 1,
"self": 0.09151850599846512
}
}
}
}
}
}
}