{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1633545458316803, "min": 0.1633545458316803, "max": 1.4926048517227173, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4882.3408203125, "min": 4882.3408203125, "max": 45279.66015625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999978.0, "min": 29952.0, "max": 2999978.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999978.0, "min": 29952.0, "max": 2999978.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8405820727348328, "min": -0.09685921669006348, "max": 0.9135556817054749, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 259.7398681640625, "min": -23.34307098388672, "max": 279.54803466796875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010829371400177479, "min": -0.027831468731164932, "max": 0.40973639488220215, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.346275806427002, "min": -7.458833694458008, "max": 97.10752868652344, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750555562275444, "min": 0.06423701543663564, "max": 0.07431860277752599, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0125833343413166, "min": 0.4883432377659349, "max": 1.1147790416628898, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01616635894778739, "min": 0.00043275881747150595, "max": 0.0182875675714887, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24249538421681083, "min": 0.0030293117223005417, "max": 0.24249538421681083, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4901461699844463e-06, "min": 1.4901461699844463e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2352192549766694e-05, "min": 2.2352192549766694e-05, "max": 0.0039376747874418, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049668222222223, "min": 0.10049668222222223, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074502333333335, "min": 1.3757013333333334, "max": 2.8125582000000007, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.961855400000007e-05, "min": 5.961855400000007e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000894278310000001, "min": 0.000894278310000001, "max": 0.13127456418, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006217288319021463, "min": 0.006211538333445787, "max": 0.6633972525596619, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09325932711362839, "min": 0.0869615375995636, "max": 4.643780708312988, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 200.88741721854305, "min": 198.17105263157896, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30334.0, "min": 15984.0, "max": 32564.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7865078766879283, "min": -1.0000000521540642, "max": 1.7959602534376233, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 271.5491972565651, "min": -32.000001668930054, "max": 271.5491972565651, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7865078766879283, "min": -1.0000000521540642, "max": 1.7959602534376233, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 271.5491972565651, "min": -32.000001668930054, "max": 271.5491972565651, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012982652716010833, "min": 0.012982652716010833, "max": 15.005418419837952, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9733632128336467, "min": 1.901483023961191, "max": 240.08669471740723, "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": "1758377046", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1758382449" }, "total": 5402.653601971, "count": 1, "self": 0.3217230859991105, "children": { "run_training.setup": { "total": 0.023394103000100586, "count": 1, "self": 0.023394103000100586 }, "TrainerController.start_learning": { "total": 5402.308484782001, "count": 1, "self": 4.729641897149122, "children": { "TrainerController._reset_env": { "total": 2.1123651289999543, "count": 1, "self": 2.1123651289999543 }, "TrainerController.advance": { "total": 5395.381333574852, "count": 195432, "self": 4.505903069098167, "children": { "env_step": { "total": 3471.517611033956, "count": 195432, "self": 3017.977094033728, "children": { "SubprocessEnvManager._take_step": { "total": 450.83082926205, "count": 195432, "self": 14.046490210973843, "children": { "TorchPolicy.evaluate": { "total": 436.78433905107613, "count": 187555, "self": 436.78433905107613 } } }, "workers": { "total": 2.709687738178218, "count": 195432, "self": 0.0, "children": { "worker_root": { "total": 5394.906215162916, "count": 195432, "is_parallel": true, "self": 2664.9223253160244, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018737550001333148, "count": 1, "is_parallel": true, "self": 0.0006559320001997548, "children": { "_process_rank_one_or_two_observation": { "total": 0.00121782299993356, "count": 8, "is_parallel": true, "self": 0.00121782299993356 } } }, "UnityEnvironment.step": { "total": 0.03708950800000821, "count": 1, "is_parallel": true, "self": 0.0003301699998701224, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029091300007166865, "count": 1, "is_parallel": true, "self": 0.00029091300007166865 }, "communicator.exchange": { "total": 0.03541544599988811, "count": 1, "is_parallel": true, "self": 0.03541544599988811 }, "steps_from_proto": { "total": 0.0010529790001783113, "count": 1, "is_parallel": true, "self": 0.00023618200020791846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008167969999703928, "count": 8, "is_parallel": true, "self": 0.0008167969999703928 } } } } } } }, "UnityEnvironment.step": { "total": 2729.9838898468915, "count": 195431, "is_parallel": true, "self": 61.28904803997193, "children": { "UnityEnvironment._generate_step_input": { "total": 40.98408174887277, "count": 195431, "is_parallel": true, "self": 40.98408174887277 }, "communicator.exchange": { "total": 2445.3938188840593, "count": 195431, "is_parallel": true, "self": 2445.3938188840593 }, "steps_from_proto": { "total": 182.31694117398752, "count": 195431, "is_parallel": true, "self": 39.769998552588504, "children": { "_process_rank_one_or_two_observation": { "total": 142.546942621399, "count": 1563448, "is_parallel": true, "self": 142.546942621399 } } } } } } } } } } }, "trainer_advance": { "total": 1919.3578194717975, "count": 195432, "self": 9.179399073731474, "children": { "process_trajectory": { "total": 370.0315606780721, "count": 195432, "self": 369.5080737890728, "children": { "RLTrainer._checkpoint": { "total": 0.5234868889992867, "count": 6, "self": 0.5234868889992867 } } }, "_update_policy": { "total": 1540.146859719994, "count": 1380, "self": 841.0307062110762, "children": { "TorchPPOOptimizer.update": { "total": 699.1161535089177, "count": 68502, "self": 699.1161535089177 } } } } } } }, "trainer_threads": { "total": 1.180999788630288e-06, "count": 1, "self": 1.180999788630288e-06 }, "TrainerController._save_models": { "total": 0.08514300000024377, "count": 1, "self": 0.0013335719995666295, "children": { "RLTrainer._checkpoint": { "total": 0.08380942800067714, "count": 1, "self": 0.08380942800067714 } } } } } } }