{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29010871052742004, "min": 0.28967219591140747, "max": 1.4201050996780396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8717.1865234375, "min": 8666.9921875, "max": 43080.30859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.565032958984375, "min": -0.09078627824783325, "max": 0.5994598865509033, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.68896484375, "min": -21.879493713378906, "max": 169.0476837158203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013102969154715538, "min": -0.05149155482649803, "max": 0.5854023694992065, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.564007520675659, "min": -13.490787506103516, "max": 138.7403564453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06925368377484291, "min": 0.06613300761541668, "max": 0.07506670230042573, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9695515728478008, "min": 0.5054248336606577, "max": 1.085479220827384, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01440242283951236, "min": 0.00030848678303165965, "max": 0.01571312938981604, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20163391975317305, "min": 0.0040103281794115755, "max": 0.21998381145742454, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.744361704292854e-06, "min": 7.744361704292854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010842106386009996, "min": 0.00010842106386009996, "max": 0.0034929280356906997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258142142857143, "min": 0.10258142142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361399000000001, "min": 1.3886848, "max": 2.527537, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002678840007142856, "min": 0.0002678840007142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037503760099999984, "min": 0.0037503760099999984, "max": 0.11644449907, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014360090717673302, "min": 0.014204817824065685, "max": 0.5421449542045593, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20104126632213593, "min": 0.19886745512485504, "max": 3.7950146198272705, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 346.54761904761904, "min": 314.2258064516129, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29110.0, "min": 15984.0, "max": 33125.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.629638076715526, "min": -1.0000000521540642, "max": 1.642750516053169, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.8895984441042, "min": -30.463601663708687, "max": 152.77579799294472, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.629638076715526, "min": -1.0000000521540642, "max": 1.642750516053169, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.8895984441042, "min": -30.463601663708687, "max": 152.77579799294472, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.051636189127401894, "min": 0.04994475566631844, "max": 11.260127009823918, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.337439886701759, "min": 4.2647237045748625, "max": 180.1620321571827, "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": "1782157848", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/env/py310/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 2 --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": "1782160426" }, "total": 2578.7700127869994, "count": 1, "self": 0.4270502029985437, "children": { "run_training.setup": { "total": 0.024317753000104858, "count": 1, "self": 0.024317753000104858 }, "TrainerController.start_learning": { "total": 2578.3186448310007, "count": 1, "self": 1.3767602889247428, "children": { "TrainerController._reset_env": { "total": 2.85560293799972, "count": 1, "self": 2.85560293799972 }, "TrainerController.advance": { "total": 2574.008934637078, "count": 63875, "self": 1.3916544699195583, "children": { "env_step": { "total": 1934.8630425281608, "count": 63875, "self": 1781.4818960892462, "children": { "SubprocessEnvManager._take_step": { "total": 152.52995557210306, "count": 63875, "self": 4.704329792834869, "children": { "TorchPolicy.evaluate": { "total": 147.8256257792682, "count": 62559, "self": 147.8256257792682 } } }, "workers": { "total": 0.8511908668115211, "count": 63875, "self": 0.0, "children": { "worker_root": { "total": 2572.273079485204, "count": 63875, "is_parallel": true, "self": 910.071756786584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025745029997779056, "count": 1, "is_parallel": true, "self": 0.0006985610007177456, "children": { "_process_rank_one_or_two_observation": { "total": 0.00187594199906016, "count": 8, "is_parallel": true, "self": 0.00187594199906016 } } }, "UnityEnvironment.step": { "total": 0.05431029000010312, "count": 1, "is_parallel": true, "self": 0.0005840539997734595, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004572950001602294, "count": 1, "is_parallel": true, "self": 0.0004572950001602294 }, "communicator.exchange": { "total": 0.051337142000193126, "count": 1, "is_parallel": true, "self": 0.051337142000193126 }, "steps_from_proto": { "total": 0.0019317989999763086, "count": 1, "is_parallel": true, "self": 0.0003975529989475035, "children": { "_process_rank_one_or_two_observation": { "total": 0.001534246001028805, "count": 8, "is_parallel": true, "self": 0.001534246001028805 } } } } } } }, "UnityEnvironment.step": { "total": 1662.20132269862, "count": 63874, "is_parallel": true, "self": 33.787078112688505, "children": { "UnityEnvironment._generate_step_input": { "total": 24.319504085090557, "count": 63874, "is_parallel": true, "self": 24.319504085090557 }, "communicator.exchange": { "total": 1489.7498081190497, "count": 63874, "is_parallel": true, "self": 1489.7498081190497 }, "steps_from_proto": { "total": 114.3449323817913, "count": 63874, "is_parallel": true, "self": 23.80874632185987, "children": { "_process_rank_one_or_two_observation": { "total": 90.53618605993142, "count": 510992, "is_parallel": true, "self": 90.53618605993142 } } } } } } } } } } }, "trainer_advance": { "total": 637.7542376389974, "count": 63875, "self": 2.6083143510059017, "children": { "process_trajectory": { "total": 113.30397695900592, "count": 63875, "self": 113.05157624300864, "children": { "RLTrainer._checkpoint": { "total": 0.25240071599728253, "count": 2, "self": 0.25240071599728253 } } }, "_update_policy": { "total": 521.8419463289856, "count": 454, "self": 278.5588109348655, "children": { "TorchPPOOptimizer.update": { "total": 243.2831353941201, "count": 22803, "self": 243.2831353941201 } } } } } } }, "trainer_threads": { "total": 8.639999578008428e-07, "count": 1, "self": 8.639999578008428e-07 }, "TrainerController._save_models": { "total": 0.0773461029984901, "count": 1, "self": 0.0009508419989288086, "children": { "RLTrainer._checkpoint": { "total": 0.07639526099956129, "count": 1, "self": 0.07639526099956129 } } } } } } }