{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29337814450263977, "min": 0.25486496090888977, "max": 1.4549142122268677, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8932.77734375, "min": 7686.7275390625, "max": 44136.27734375, "count": 50 }, "Pyramids.Step.mean": { "value": 1499990.0, "min": 29952.0, "max": 1499990.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499990.0, "min": 29952.0, "max": 1499990.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6636287569999695, "min": -0.1311245709657669, "max": 0.6915754079818726, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 189.79782104492188, "min": -31.076522827148438, "max": 197.7905731201172, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004196369554847479, "min": -0.0021300276275724173, "max": 0.3739135265350342, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2001616954803467, "min": -0.52398681640625, "max": 88.61750793457031, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06900182120023399, "min": 0.06458475187814439, "max": 0.07428428931632966, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0350273180035099, "min": 0.5072181997743794, "max": 1.0711135286232913, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014552214802501516, "min": 0.00019361602816145963, "max": 0.01641706984050365, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21828322203752273, "min": 0.002517008366098975, "max": 0.24625604760755473, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00015151583616140445, "min": 0.00015151583616140445, "max": 0.00029838354339596195, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022727375424210668, "min": 0.0020886848037717336, "max": 0.0040528428490524, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15050526222222224, "min": 0.15050526222222224, "max": 0.19946118095238097, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.257578933333334, "min": 1.3962282666666668, "max": 2.8425425, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.005055475695999999, "min": 0.005055475695999999, "max": 0.009946171977142856, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.07583213543999999, "min": 0.06962320384, "max": 0.13509966524, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009042560122907162, "min": 0.009042560122907162, "max": 0.37279942631721497, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13563840091228485, "min": 0.12803177535533905, "max": 2.609596014022827, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 305.17, "min": 298.53921568627453, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30517.0, "min": 15984.0, "max": 33842.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.654811985269189, "min": -1.0000000521540642, "max": 1.6689705097361616, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.4811985269189, "min": -30.99220159649849, "max": 169.4271976724267, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.654811985269189, "min": -1.0000000521540642, "max": 1.6689705097361616, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.4811985269189, "min": -30.99220159649849, "max": 169.4271976724267, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02900079621147597, "min": 0.028952121257898398, "max": 7.275598568841815, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.900079621147597, "min": 2.808773804863449, "max": 116.40957710146904, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1778085659", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]", "command_line_arguments": "/content/mlagents_venv/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": "1778089043" }, "total": 3384.055421287, "count": 1, "self": 0.5299562499999411, "children": { "run_training.setup": { "total": 0.024651114999869606, "count": 1, "self": 0.024651114999869606 }, "TrainerController.start_learning": { "total": 3383.5008139220004, "count": 1, "self": 2.2091734360810733, "children": { "TrainerController._reset_env": { "total": 2.501782992999779, "count": 1, "self": 2.501782992999779 }, "TrainerController.advance": { "total": 3378.786365349919, "count": 96205, "self": 2.136132311030906, "children": { "env_step": { "total": 2369.861654291928, "count": 96205, "self": 2136.7773060357654, "children": { "SubprocessEnvManager._take_step": { "total": 231.75809718604978, "count": 96205, "self": 7.1928093941751285, "children": { "TorchPolicy.evaluate": { "total": 224.56528779187465, "count": 93837, "self": 224.56528779187465 } } }, "workers": { "total": 1.326251070112903, "count": 96204, "self": 0.0, "children": { "worker_root": { "total": 3374.6311190030506, "count": 96204, "is_parallel": true, "self": 1415.765940330129, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026714369996625464, "count": 1, "is_parallel": true, "self": 0.0007815329995537468, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018899040001087997, "count": 8, "is_parallel": true, "self": 0.0018899040001087997 } } }, "UnityEnvironment.step": { "total": 0.05064881799989962, "count": 1, "is_parallel": true, "self": 0.0005091709995213023, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004723710003418091, "count": 1, "is_parallel": true, "self": 0.0004723710003418091 }, "communicator.exchange": { "total": 0.04807566399995267, "count": 1, "is_parallel": true, "self": 0.04807566399995267 }, "steps_from_proto": { "total": 0.0015916120000838418, "count": 1, "is_parallel": true, "self": 0.0003565829997569381, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012350290003269038, "count": 8, "is_parallel": true, "self": 0.0012350290003269038 } } } } } } }, "UnityEnvironment.step": { "total": 1958.8651786729215, "count": 96203, "is_parallel": true, "self": 50.77243194004859, "children": { "UnityEnvironment._generate_step_input": { "total": 35.88544407901691, "count": 96203, "is_parallel": true, "self": 35.88544407901691 }, "communicator.exchange": { "total": 1704.0718452139358, "count": 96203, "is_parallel": true, "self": 1704.0718452139358 }, "steps_from_proto": { "total": 168.13545743992017, "count": 96203, "is_parallel": true, "self": 34.78812678711574, "children": { "_process_rank_one_or_two_observation": { "total": 133.34733065280443, "count": 769624, "is_parallel": true, "self": 133.34733065280443 } } } } } } } } } } }, "trainer_advance": { "total": 1006.78857874696, "count": 96204, "self": 4.202058174977083, "children": { "process_trajectory": { "total": 192.83659642696875, "count": 96204, "self": 192.56374829596825, "children": { "RLTrainer._checkpoint": { "total": 0.27284813100050087, "count": 3, "self": 0.27284813100050087 } } }, "_update_policy": { "total": 809.7499241450141, "count": 691, "self": 447.08472683198625, "children": { "TorchPPOOptimizer.update": { "total": 362.6651973130279, "count": 34239, "self": 362.6651973130279 } } } } } } }, "trainer_threads": { "total": 1.7250004020752385e-06, "count": 1, "self": 1.7250004020752385e-06 }, "TrainerController._save_models": { "total": 0.0034904180001831264, "count": 1, "self": 4.294199970900081e-05, "children": { "RLTrainer._checkpoint": { "total": 0.0034474760004741256, "count": 1, "self": 0.0034474760004741256 } } } } } } }