{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30823203921318054, "min": 0.2590036988258362, "max": 1.3212605714797974, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9316.0048828125, "min": 7811.55126953125, "max": 40081.76171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29989.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29989.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6038783192634583, "min": -0.10377731919288635, "max": 0.6722452640533447, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 169.0859375, "min": -25.010334014892578, "max": 191.58990478515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027300408110022545, "min": 0.00039116060361266136, "max": 0.3165760338306427, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.644114017486572, "min": 0.10913380980491638, "max": 75.3450927734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06567606225767772, "min": 0.0656227797144156, "max": 0.0743524374070947, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.919464871607488, "min": 0.5204670618496628, "max": 1.0589628908686186, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014384692752390125, "min": 0.00022428097407098583, "max": 0.016094682862915634, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20138569853346175, "min": 0.00269137168885183, "max": 0.23286290983863486, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.289326141685715e-06, "min": 7.289326141685715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010205056598360001, "min": 0.00010205056598360001, "max": 0.003331593089469, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242974285714286, "min": 0.10242974285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340164, "min": 1.3886848, "max": 2.442952, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002527313114285715, "min": 0.0002527313114285715, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035382383600000007, "min": 0.0035382383600000007, "max": 0.11106204690000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013543262146413326, "min": 0.012501879595220089, "max": 0.4942598342895508, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18960566818714142, "min": 0.1750263124704361, "max": 3.4598188400268555, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.3440860215054, "min": 287.7289719626168, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27932.0, "min": 16788.0, "max": 32541.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.635126870165589, "min": -0.999837551265955, "max": 1.6748784882164447, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 152.06679892539978, "min": -31.99480164051056, "max": 179.21199823915958, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.635126870165589, "min": -0.999837551265955, "max": 1.6748784882164447, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 152.06679892539978, "min": -31.99480164051056, "max": 179.21199823915958, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04253368296501507, "min": 0.0420990171978795, "max": 8.939846154521494, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9556325157464016, "min": 3.9556325157464016, "max": 151.9773846268654, "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": "1725455468", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725458277" }, "total": 2808.690324873, "count": 1, "self": 0.5417087249998076, "children": { "run_training.setup": { "total": 0.07583376699994915, "count": 1, "self": 0.07583376699994915 }, "TrainerController.start_learning": { "total": 2808.0727823810003, "count": 1, "self": 1.8343723190228047, "children": { "TrainerController._reset_env": { "total": 1.872349722999843, "count": 1, "self": 1.872349722999843 }, "TrainerController.advance": { "total": 2804.293062076978, "count": 63878, "self": 1.8592885488969841, "children": { "env_step": { "total": 1861.1480081190616, "count": 63878, "self": 1729.754723312018, "children": { "SubprocessEnvManager._take_step": { "total": 130.27318121500457, "count": 63878, "self": 5.305852125036381, "children": { "TorchPolicy.evaluate": { "total": 124.96732908996819, "count": 62566, "self": 124.96732908996819 } } }, "workers": { "total": 1.1201035920389586, "count": 63878, "self": 0.0, "children": { "worker_root": { "total": 2802.454026264935, "count": 63878, "is_parallel": true, "self": 1220.0774426239313, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006555874000241602, "count": 1, "is_parallel": true, "self": 0.002710352000576677, "children": { "_process_rank_one_or_two_observation": { "total": 0.003845521999664925, "count": 8, "is_parallel": true, "self": 0.003845521999664925 } } }, "UnityEnvironment.step": { "total": 0.056553943999915646, "count": 1, "is_parallel": true, "self": 0.000700233000316075, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005066229996373295, "count": 1, "is_parallel": true, "self": 0.0005066229996373295 }, "communicator.exchange": { "total": 0.053332365000187565, "count": 1, "is_parallel": true, "self": 0.053332365000187565 }, "steps_from_proto": { "total": 0.0020147229997746763, "count": 1, "is_parallel": true, "self": 0.0005138159995112801, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015009070002633962, "count": 8, "is_parallel": true, "self": 0.0015009070002633962 } } } } } } }, "UnityEnvironment.step": { "total": 1582.3765836410034, "count": 63877, "is_parallel": true, "self": 41.761416157960866, "children": { "UnityEnvironment._generate_step_input": { "total": 27.802824746935585, "count": 63877, "is_parallel": true, "self": 27.802824746935585 }, "communicator.exchange": { "total": 1393.7710841601047, "count": 63877, "is_parallel": true, "self": 1393.7710841601047 }, "steps_from_proto": { "total": 119.04125857600229, "count": 63877, "is_parallel": true, "self": 25.022369727780642, "children": { "_process_rank_one_or_two_observation": { "total": 94.01888884822165, "count": 511016, "is_parallel": true, "self": 94.01888884822165 } } } } } } } } } } }, "trainer_advance": { "total": 941.2857654090194, "count": 63878, "self": 3.304072214232292, "children": { "process_trajectory": { "total": 143.5407350457849, "count": 63878, "self": 143.38364553978454, "children": { "RLTrainer._checkpoint": { "total": 0.15708950600037497, "count": 2, "self": 0.15708950600037497 } } }, "_update_policy": { "total": 794.4409581490022, "count": 451, "self": 340.7522739279957, "children": { "TorchPPOOptimizer.update": { "total": 453.6886842210065, "count": 22842, "self": 453.6886842210065 } } } } } } }, "trainer_threads": { "total": 1.0789999578264542e-06, "count": 1, "self": 1.0789999578264542e-06 }, "TrainerController._save_models": { "total": 0.07299718299964297, "count": 1, "self": 0.0017966440000236616, "children": { "RLTrainer._checkpoint": { "total": 0.07120053899961931, "count": 1, "self": 0.07120053899961931 } } } } } } }