{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14018405973911285, "min": 0.13309766352176666, "max": 1.4802470207214355, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4203.27880859375, "min": 3990.9775390625, "max": 44904.7734375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999945.0, "min": 29910.0, "max": 2999945.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999945.0, "min": 29910.0, "max": 2999945.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6469378471374512, "min": -0.09215991199016571, "max": 0.7879016399383545, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.61196899414062, "min": -22.210538864135742, "max": 238.73419189453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01199105754494667, "min": -0.051263272762298584, "max": 0.40548187494277954, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -3.4774067401885986, "min": -14.251190185546875, "max": 96.09920501708984, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06679901297106614, "min": 0.06201395759338132, "max": 0.0743304349184744, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9351861815949258, "min": 0.5946434793477952, "max": 1.107122581436153, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01804359516489883, "min": 0.0006677828771224249, "max": 0.01804359516489883, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2526103323085836, "min": 0.008681177402591524, "max": 0.2526103323085836, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4910995029999994e-06, "min": 1.4910995029999994e-06, "max": 0.000298403025532325, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.087539304199999e-05, "min": 2.087539304199999e-05, "max": 0.004011415662861466, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049699999999999, "min": 0.10049699999999999, "max": 0.19946767500000004, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406958, "min": 1.406958, "max": 2.7824929333333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.965029999999999e-05, "min": 5.965029999999999e-05, "max": 0.0099468207325, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008351041999999998, "min": 0.0008351041999999998, "max": 0.13372013948, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005037582013756037, "min": 0.004874700214713812, "max": 0.5023132562637329, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07052614539861679, "min": 0.06857124716043472, "max": 4.018506050109863, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.34188034188034, "min": 222.00757575757575, "max": 990.4117647058823, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29173.0, "min": 16837.0, "max": 32820.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6800152353184707, "min": -0.9181467160582543, "max": 1.7631187828859889, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 198.24179776757956, "min": -28.133801601827145, "max": 234.49479812383652, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6800152353184707, "min": -0.9181467160582543, "max": 1.7631187828859889, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 198.24179776757956, "min": -28.133801601827145, "max": 234.49479812383652, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.013265099109541892, "min": 0.013184731567369974, "max": 9.68146879445104, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5652816949259432, "min": 1.5011348447806085, "max": 164.5849695056677, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741164253", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741171472" }, "total": 7219.305083765, "count": 1, "self": 0.6993196639996313, "children": { "run_training.setup": { "total": 0.021329560000026504, "count": 1, "self": 0.021329560000026504 }, "TrainerController.start_learning": { "total": 7218.5844345410005, "count": 1, "self": 5.758124527009386, "children": { "TrainerController._reset_env": { "total": 2.5757131290000075, "count": 1, "self": 2.5757131290000075 }, "TrainerController.advance": { "total": 7210.19444245499, "count": 193681, "self": 5.274296127016896, "children": { "env_step": { "total": 4994.420883087939, "count": 193681, "self": 4616.65551173627, "children": { "SubprocessEnvManager._take_step": { "total": 374.1638826948218, "count": 193681, "self": 13.988461763911118, "children": { "TorchPolicy.evaluate": { "total": 360.17542093091066, "count": 187552, "self": 360.17542093091066 } } }, "workers": { "total": 3.601488656847607, "count": 193681, "self": 0.0, "children": { "worker_root": { "total": 7201.635875997229, "count": 193681, "is_parallel": true, "self": 2984.1568096001993, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005293120000033014, "count": 1, "is_parallel": true, "self": 0.004322580000007292, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009705400000257214, "count": 8, "is_parallel": true, "self": 0.0009705400000257214 } } }, "UnityEnvironment.step": { "total": 0.048801508999986254, "count": 1, "is_parallel": true, "self": 0.000495940000007522, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004072099999916645, "count": 1, "is_parallel": true, "self": 0.0004072099999916645 }, "communicator.exchange": { "total": 0.04648465899998655, "count": 1, "is_parallel": true, "self": 0.04648465899998655 }, "steps_from_proto": { "total": 0.0014137000000005173, "count": 1, "is_parallel": true, "self": 0.00031538999979829896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010983100002022184, "count": 8, "is_parallel": true, "self": 0.0010983100002022184 } } } } } } }, "UnityEnvironment.step": { "total": 4217.47906639703, "count": 193680, "is_parallel": true, "self": 99.85155283602853, "children": { "UnityEnvironment._generate_step_input": { "total": 73.70786060100676, "count": 193680, "is_parallel": true, "self": 73.70786060100676 }, "communicator.exchange": { "total": 3769.07010360406, "count": 193680, "is_parallel": true, "self": 3769.07010360406 }, "steps_from_proto": { "total": 274.8495493559348, "count": 193680, "is_parallel": true, "self": 59.3619097557596, "children": { "_process_rank_one_or_two_observation": { "total": 215.4876396001752, "count": 1549440, "is_parallel": true, "self": 215.4876396001752 } } } } } } } } } } }, "trainer_advance": { "total": 2210.4992632400345, "count": 193681, "self": 11.373777961089218, "children": { "process_trajectory": { "total": 358.8807158179537, "count": 193681, "self": 358.32651780195636, "children": { "RLTrainer._checkpoint": { "total": 0.5541980159973718, "count": 6, "self": 0.5541980159973718 } } }, "_update_policy": { "total": 1840.2447694609916, "count": 1401, "self": 734.5447293889583, "children": { "TorchPPOOptimizer.update": { "total": 1105.7000400720333, "count": 68298, "self": 1105.7000400720333 } } } } } } }, "trainer_threads": { "total": 8.510005500284024e-07, "count": 1, "self": 8.510005500284024e-07 }, "TrainerController._save_models": { "total": 0.056153579000238096, "count": 1, "self": 0.001366500000585802, "children": { "RLTrainer._checkpoint": { "total": 0.054787078999652294, "count": 1, "self": 0.054787078999652294 } } } } } } }