{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4913412928581238, "min": 0.4913412928581238, "max": 1.439706563949585, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14810.9921875, "min": 14810.9921875, "max": 43674.9375, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29982.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29982.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.37251564860343933, "min": -0.1004050001502037, "max": 0.4193427562713623, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 98.71664428710938, "min": -24.19760513305664, "max": 112.14228820800781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014797584153711796, "min": -0.038920387625694275, "max": 0.45125487446784973, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9213597774505615, "min": -9.885778427124023, "max": 107.3986587524414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07138498777637606, "min": 0.06538585452937071, "max": 0.07294094735663662, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9993898288692649, "min": 0.5056615078995063, "max": 1.036158256601387, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013427846303318251, "min": 0.00013116746736695312, "max": 0.016707347589015053, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1879898482464555, "min": 0.0018363445431373439, "max": 0.23390286624621073, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.621404602421429e-06, "min": 7.621404602421429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001066996644339, "min": 0.0001066996644339, "max": 0.0033820706726432, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254043571428571, "min": 0.10254043571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355661, "min": 1.3886848, "max": 2.5273568000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002637895278571429, "min": 0.0002637895278571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00369305339, "min": 0.00369305339, "max": 0.11276294432, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012463592924177647, "min": 0.01187005452811718, "max": 0.39912012219429016, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1744903028011322, "min": 0.16618075966835022, "max": 2.7938408851623535, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 440.8888888888889, "min": 403.7837837837838, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27776.0, "min": 16781.0, "max": 33476.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.336844422159687, "min": -0.9999742455059483, "max": 1.522850676531523, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.22119859606028, "min": -30.999201610684395, "max": 112.118398450315, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.336844422159687, "min": -0.9999742455059483, "max": 1.522850676531523, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.22119859606028, "min": -30.999201610684395, "max": 112.118398450315, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05540553152206398, "min": 0.054392140985598685, "max": 7.816912961795049, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.490548485890031, "min": 3.490548485890031, "max": 132.88752035051584, "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": "1743352000", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "1743354093" }, "total": 2093.824530574, "count": 1, "self": 0.4790714040000239, "children": { "run_training.setup": { "total": 0.01985053900011735, "count": 1, "self": 0.01985053900011735 }, "TrainerController.start_learning": { "total": 2093.325608631, "count": 1, "self": 1.2803749259469441, "children": { "TrainerController._reset_env": { "total": 2.8496536909999577, "count": 1, "self": 2.8496536909999577 }, "TrainerController.advance": { "total": 2089.113223817053, "count": 63463, "self": 1.3799092570925495, "children": { "env_step": { "total": 1422.3375799709568, "count": 63463, "self": 1275.0725231447923, "children": { "SubprocessEnvManager._take_step": { "total": 146.51980230110598, "count": 63463, "self": 4.503664570074761, "children": { "TorchPolicy.evaluate": { "total": 142.01613773103122, "count": 62552, "self": 142.01613773103122 } } }, "workers": { "total": 0.745254525058499, "count": 63463, "self": 0.0, "children": { "worker_root": { "total": 2088.5943062750334, "count": 63463, "is_parallel": true, "self": 920.9232588840498, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002515399999992951, "count": 1, "is_parallel": true, "self": 0.0007670340003187448, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017483659996742063, "count": 8, "is_parallel": true, "self": 0.0017483659996742063 } } }, "UnityEnvironment.step": { "total": 0.046445869999843126, "count": 1, "is_parallel": true, "self": 0.0005415250000169181, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004546879999907105, "count": 1, "is_parallel": true, "self": 0.0004546879999907105 }, "communicator.exchange": { "total": 0.043894980999994004, "count": 1, "is_parallel": true, "self": 0.043894980999994004 }, "steps_from_proto": { "total": 0.0015546759998414927, "count": 1, "is_parallel": true, "self": 0.0003299809993677627, "children": { "_process_rank_one_or_two_observation": { "total": 0.00122469500047373, "count": 8, "is_parallel": true, "self": 0.00122469500047373 } } } } } } }, "UnityEnvironment.step": { "total": 1167.6710473909836, "count": 63462, "is_parallel": true, "self": 30.810180833009554, "children": { "UnityEnvironment._generate_step_input": { "total": 22.346455694029373, "count": 63462, "is_parallel": true, "self": 22.346455694029373 }, "communicator.exchange": { "total": 1022.9814092159768, "count": 63462, "is_parallel": true, "self": 1022.9814092159768 }, "steps_from_proto": { "total": 91.53300164796792, "count": 63462, "is_parallel": true, "self": 18.05196841886027, "children": { "_process_rank_one_or_two_observation": { "total": 73.48103322910765, "count": 507696, "is_parallel": true, "self": 73.48103322910765 } } } } } } } } } } }, "trainer_advance": { "total": 665.3957345890037, "count": 63463, "self": 2.3748772450144315, "children": { "process_trajectory": { "total": 124.00513473099295, "count": 63463, "self": 123.80023607199269, "children": { "RLTrainer._checkpoint": { "total": 0.20489865900026416, "count": 2, "self": 0.20489865900026416 } } }, "_update_policy": { "total": 539.0157226129963, "count": 446, "self": 294.37971499597984, "children": { "TorchPPOOptimizer.update": { "total": 244.6360076170165, "count": 22869, "self": 244.6360076170165 } } } } } } }, "trainer_threads": { "total": 9.750001481734216e-07, "count": 1, "self": 9.750001481734216e-07 }, "TrainerController._save_models": { "total": 0.08235522199993284, "count": 1, "self": 0.0014555510001628136, "children": { "RLTrainer._checkpoint": { "total": 0.08089967099977002, "count": 1, "self": 0.08089967099977002 } } } } } } }