{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5533747673034668, "min": 0.5533747673034668, "max": 1.359647512435913, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 16707.490234375, "min": 16707.490234375, "max": 41246.265625, "count": 35 }, "Pyramids.Step.mean": { "value": 1049980.0, "min": 29940.0, "max": 1049980.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049980.0, "min": 29940.0, "max": 1049980.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5745955109596252, "min": -0.105750173330307, "max": 0.6081712245941162, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.1629638671875, "min": -25.380041122436523, "max": 174.54513549804688, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011620656587183475, "min": -0.008183085359632969, "max": 0.3403794467449188, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2189218997955322, "min": -2.2012500762939453, "max": 80.66992950439453, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0667015266405723, "min": 0.06567240418960518, "max": 0.0735768778006682, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9338213729680123, "min": 0.480553581819424, "max": 1.0670807742280883, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013769543542544923, "min": 0.0005767750671712414, "max": 0.015281075727555205, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19277360959562892, "min": 0.007498075873226138, "max": 0.22921613591332807, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001964118131008357, "min": 0.0001964118131008357, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027497653834117, "min": 0.0020886848037717336, "max": 0.0040114803628399, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16547059285714288, "min": 0.16547059285714288, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3165883000000003, "min": 1.3962282666666668, "max": 2.7376231, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006550512226428571, "min": 0.006550512226428571, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09170717116999999, "min": 0.06962320384, "max": 0.13372229399000002, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008156410418450832, "min": 0.008156410418450832, "max": 0.48774033784866333, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1141897514462471, "min": 0.1141897514462471, "max": 3.414182424545288, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 331.27272727272725, "min": 316.44444444444446, "max": 996.9032258064516, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29152.0, "min": 16867.0, "max": 32960.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.623319529853333, "min": -0.9333290835061381, "max": 1.623319529853333, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 141.22879909723997, "min": -30.08520172536373, "max": 158.66919802874327, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.623319529853333, "min": -0.9333290835061381, "max": 1.623319529853333, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 141.22879909723997, "min": -30.08520172536373, "max": 158.66919802874327, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028302806005217725, "min": 0.02765637055827855, "max": 9.412102928056436, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 2.462344122453942, "min": 2.377634520009451, "max": 160.00574977695942, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1761579563", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/content/py310/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": "1761581989" }, "total": 2425.0919318979995, "count": 1, "self": 0.4770708769997327, "children": { "run_training.setup": { "total": 0.019174604999989242, "count": 1, "self": 0.019174604999989242 }, "TrainerController.start_learning": { "total": 2424.595686416, "count": 1, "self": 1.6790527299240239, "children": { "TrainerController._reset_env": { "total": 2.104101265000054, "count": 1, "self": 2.104101265000054 }, "TrainerController.advance": { "total": 2420.8091348040757, "count": 68717, "self": 1.7283294280091468, "children": { "env_step": { "total": 1698.910874452022, "count": 68717, "self": 1523.3656110320178, "children": { "SubprocessEnvManager._take_step": { "total": 174.51509017100557, "count": 68717, "self": 5.316212593007549, "children": { "TorchPolicy.evaluate": { "total": 169.19887757799802, "count": 67455, "self": 169.19887757799802 } } }, "workers": { "total": 1.030173248998608, "count": 68717, "self": 0.0, "children": { "worker_root": { "total": 2417.9212485079956, "count": 68717, "is_parallel": true, "self": 1027.4005853459591, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001925556000060169, "count": 1, "is_parallel": true, "self": 0.0007004619999406714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012250940001194977, "count": 8, "is_parallel": true, "self": 0.0012250940001194977 } } }, "UnityEnvironment.step": { "total": 0.1180359850000059, "count": 1, "is_parallel": true, "self": 0.0005365819999951782, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044879799997943337, "count": 1, "is_parallel": true, "self": 0.00044879799997943337 }, "communicator.exchange": { "total": 0.11141382999994676, "count": 1, "is_parallel": true, "self": 0.11141382999994676 }, "steps_from_proto": { "total": 0.005636775000084526, "count": 1, "is_parallel": true, "self": 0.0003420260004531883, "children": { "_process_rank_one_or_two_observation": { "total": 0.005294748999631338, "count": 8, "is_parallel": true, "self": 0.005294748999631338 } } } } } } }, "UnityEnvironment.step": { "total": 1390.5206631620365, "count": 68716, "is_parallel": true, "self": 37.259826141993926, "children": { "UnityEnvironment._generate_step_input": { "total": 26.526520999008426, "count": 68716, "is_parallel": true, "self": 26.526520999008426 }, "communicator.exchange": { "total": 1205.0022243769863, "count": 68716, "is_parallel": true, "self": 1205.0022243769863 }, "steps_from_proto": { "total": 121.73209164404784, "count": 68716, "is_parallel": true, "self": 25.862182486997654, "children": { "_process_rank_one_or_two_observation": { "total": 95.86990915705019, "count": 549728, "is_parallel": true, "self": 95.86990915705019 } } } } } } } } } } }, "trainer_advance": { "total": 720.1699309240448, "count": 68717, "self": 3.117393731028642, "children": { "process_trajectory": { "total": 138.10136608501648, "count": 68717, "self": 137.86525951801673, "children": { "RLTrainer._checkpoint": { "total": 0.23610656699975152, "count": 2, "self": 0.23610656699975152 } } }, "_update_policy": { "total": 578.9511711079997, "count": 490, "self": 321.2951333150338, "children": { "TorchPPOOptimizer.update": { "total": 257.6560377929659, "count": 24567, "self": 257.6560377929659 } } } } } } }, "trainer_threads": { "total": 1.368000084767118e-06, "count": 1, "self": 1.368000084767118e-06 }, "TrainerController._save_models": { "total": 0.0033962490001613332, "count": 1, "self": 2.479900012986036e-05, "children": { "RLTrainer._checkpoint": { "total": 0.003371450000031473, "count": 1, "self": 0.003371450000031473 } } } } } } }