{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6362375617027283, "min": 0.6313311457633972, "max": 1.4627357721328735, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18883.53125, "min": 18883.53125, "max": 44373.55078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29924.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29924.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2534390091896057, "min": -0.12295710295438766, "max": 0.2885737419128418, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 65.64070129394531, "min": -29.50970458984375, "max": 75.6063232421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01804141141474247, "min": -0.01804141141474247, "max": 0.16768185794353485, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.672725677490234, "min": -4.672725677490234, "max": 40.41132736206055, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07194950870384662, "min": 0.06615968040822932, "max": 0.07365789367364872, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0072931218538526, "min": 0.515605255715541, "max": 1.0478990673921849, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012404981810273144, "min": 6.899401456621187e-05, "max": 0.012404981810273144, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.173669745343824, "min": 0.0009659162039269662, "max": 0.173669745343824, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.47354750885e-06, "min": 7.47354750885e-06, "max": 0.00029523411587434285, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001046296651239, "min": 0.0001046296651239, "max": 0.0035082668305777996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249114999999999, "min": 0.10249114999999999, "max": 0.1984113714285714, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348760999999999, "min": 1.3888795999999999, "max": 2.5694222, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025886588500000004, "min": 0.00025886588500000004, "max": 0.009841296005714286, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036241223900000006, "min": 0.0036241223900000006, "max": 0.11696527778, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01060565747320652, "min": 0.01040094904601574, "max": 0.35427170991897583, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14847920835018158, "min": 0.14561328291893005, "max": 2.4799020290374756, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 528.4137931034483, "min": 528.4137931034483, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30648.0, "min": 16723.0, "max": 32732.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1611379030449638, "min": -0.9997852378421359, "max": 1.1611379030449638, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.3459983766079, "min": -30.76280176639557, "max": 67.3459983766079, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1611379030449638, "min": -0.9997852378421359, "max": 1.1611379030449638, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.3459983766079, "min": -30.76280176639557, "max": 67.3459983766079, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05816971184184036, "min": 0.05816971184184036, "max": 6.880389970891616, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.373843286826741, "min": 3.1480140782514354, "max": 116.96662950515747, "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": "1784336983", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1784338562" }, "total": 1579.2364225259998, "count": 1, "self": 0.32156133799981035, "children": { "run_training.setup": { "total": 0.02468523799984723, "count": 1, "self": 0.02468523799984723 }, "TrainerController.start_learning": { "total": 1578.8901759500002, "count": 1, "self": 1.242672765035195, "children": { "TrainerController._reset_env": { "total": 2.367709945999877, "count": 1, "self": 2.367709945999877 }, "TrainerController.advance": { "total": 1575.2062154749653, "count": 63388, "self": 1.1870749749882634, "children": { "env_step": { "total": 984.4209435319897, "count": 63388, "self": 844.9678011699693, "children": { "SubprocessEnvManager._take_step": { "total": 138.7116066899814, "count": 63388, "self": 4.184227928986047, "children": { "TorchPolicy.evaluate": { "total": 134.52737876099536, "count": 62567, "self": 134.52737876099536 } } }, "workers": { "total": 0.7415356720389354, "count": 63388, "self": 0.0, "children": { "worker_root": { "total": 1576.6757748989498, "count": 63388, "is_parallel": true, "self": 819.2188703679444, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018781759999910719, "count": 1, "is_parallel": true, "self": 0.0006271819997891726, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012509940002018993, "count": 8, "is_parallel": true, "self": 0.0012509940002018993 } } }, "UnityEnvironment.step": { "total": 0.03484569499983081, "count": 1, "is_parallel": true, "self": 0.0003420819996335922, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003207590000329219, "count": 1, "is_parallel": true, "self": 0.0003207590000329219 }, "communicator.exchange": { "total": 0.03316115400002673, "count": 1, "is_parallel": true, "self": 0.03316115400002673 }, "steps_from_proto": { "total": 0.001021700000137571, "count": 1, "is_parallel": true, "self": 0.00023027499992167577, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007914250002158951, "count": 8, "is_parallel": true, "self": 0.0007914250002158951 } } } } } } }, "UnityEnvironment.step": { "total": 757.4569045310054, "count": 63387, "is_parallel": true, "self": 20.013743361062552, "children": { "UnityEnvironment._generate_step_input": { "total": 13.483533401980822, "count": 63387, "is_parallel": true, "self": 13.483533401980822 }, "communicator.exchange": { "total": 666.6476047939973, "count": 63387, "is_parallel": true, "self": 666.6476047939973 }, "steps_from_proto": { "total": 57.31202297396476, "count": 63387, "is_parallel": true, "self": 12.217451158930317, "children": { "_process_rank_one_or_two_observation": { "total": 45.09457181503444, "count": 507096, "is_parallel": true, "self": 45.09457181503444 } } } } } } } } } } }, "trainer_advance": { "total": 589.5981969679874, "count": 63388, "self": 2.382095324048578, "children": { "process_trajectory": { "total": 100.31896107794546, "count": 63388, "self": 100.14229111394525, "children": { "RLTrainer._checkpoint": { "total": 0.17666996400021162, "count": 2, "self": 0.17666996400021162 } } }, "_update_policy": { "total": 486.89714056599337, "count": 451, "self": 256.99970595397326, "children": { "TorchPPOOptimizer.update": { "total": 229.8974346120201, "count": 22764, "self": 229.8974346120201 } } } } } } }, "trainer_threads": { "total": 9.919999683916103e-07, "count": 1, "self": 9.919999683916103e-07 }, "TrainerController._save_models": { "total": 0.07357677199979662, "count": 1, "self": 0.0009788159995878232, "children": { "RLTrainer._checkpoint": { "total": 0.0725979560002088, "count": 1, "self": 0.0725979560002088 } } } } } } }