{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5846028923988342, "min": 0.5846028923988342, "max": 1.4821498394012451, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17481.96484375, "min": 17481.96484375, "max": 44962.49609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29884.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29884.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3721213638782501, "min": -0.11277265846729279, "max": 0.4167194962501526, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.75155639648438, "min": -27.06543731689453, "max": 112.09754180908203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003546916414052248, "min": -0.0064742472022771835, "max": 0.17866326868534088, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9221982955932617, "min": -1.7415724992752075, "max": 42.34319305419922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07173565085191431, "min": 0.06528372986092823, "max": 0.07273674955026113, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0042991119268003, "min": 0.4960903806150918, "max": 1.090359085588716, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013970981003763547, "min": 0.00030457366726757647, "max": 0.0166651769267666, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19559373405268965, "min": 0.0033503103399433413, "max": 0.249977653901499, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.322797559099996e-06, "min": 7.322797559099996e-06, "max": 0.0002952358301594857, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010251916582739995, "min": 0.00010251916582739995, "max": 0.0032562134145955996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244089999999999, "min": 0.10244089999999999, "max": 0.19841194285714286, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341726, "min": 1.3888836, "max": 2.4431753, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025384590999999993, "min": 0.00025384590999999993, "max": 0.00984135309142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003553842739999999, "min": 0.003553842739999999, "max": 0.10856189956, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006191181484609842, "min": 0.006157424300909042, "max": 0.29541710019111633, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08667653799057007, "min": 0.08620394021272659, "max": 2.0679197311401367, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 481.41379310344826, "min": 422.0416666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27922.0, "min": 16555.0, "max": 34387.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2771413545927097, "min": -0.9999750521965325, "max": 1.4390277495193813, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 74.07419856637716, "min": -31.99920167028904, "max": 103.60999796539545, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2771413545927097, "min": -0.9999750521965325, "max": 1.4390277495193813, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 74.07419856637716, "min": -31.99920167028904, "max": 103.60999796539545, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03143329427257413, "min": 0.027785963575802777, "max": 5.425608523628291, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8231310678092996, "min": 1.8231310678092996, "max": 92.23534490168095, "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": "1766479011", "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": "1766481209" }, "total": 2197.9439772759997, "count": 1, "self": 0.47825325400026486, "children": { "run_training.setup": { "total": 0.023167831999899136, "count": 1, "self": 0.023167831999899136 }, "TrainerController.start_learning": { "total": 2197.44255619, "count": 1, "self": 1.3448346859554476, "children": { "TrainerController._reset_env": { "total": 2.0236905210001623, "count": 1, "self": 2.0236905210001623 }, "TrainerController.advance": { "total": 2193.998152698044, "count": 63450, "self": 1.3721305240319452, "children": { "env_step": { "total": 1542.542601257043, "count": 63450, "self": 1393.8587554351163, "children": { "SubprocessEnvManager._take_step": { "total": 147.87780798197946, "count": 63450, "self": 4.620466329935198, "children": { "TorchPolicy.evaluate": { "total": 143.25734165204426, "count": 62558, "self": 143.25734165204426 } } }, "workers": { "total": 0.8060378399472938, "count": 63450, "self": 0.0, "children": { "worker_root": { "total": 2191.225857128939, "count": 63450, "is_parallel": true, "self": 913.5161572529353, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026047249998555344, "count": 1, "is_parallel": true, "self": 0.0005853910004134377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020193339994420967, "count": 8, "is_parallel": true, "self": 0.0020193339994420967 } } }, "UnityEnvironment.step": { "total": 0.05367206999994778, "count": 1, "is_parallel": true, "self": 0.0006147719998352841, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004665520000344259, "count": 1, "is_parallel": true, "self": 0.0004665520000344259 }, "communicator.exchange": { "total": 0.05076658600000883, "count": 1, "is_parallel": true, "self": 0.05076658600000883 }, "steps_from_proto": { "total": 0.0018241600000692415, "count": 1, "is_parallel": true, "self": 0.0005462059998535551, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012779540002156864, "count": 8, "is_parallel": true, "self": 0.0012779540002156864 } } } } } } }, "UnityEnvironment.step": { "total": 1277.7096998760037, "count": 63449, "is_parallel": true, "self": 34.24955844488977, "children": { "UnityEnvironment._generate_step_input": { "total": 23.65027151205095, "count": 63449, "is_parallel": true, "self": 23.65027151205095 }, "communicator.exchange": { "total": 1110.0538563030195, "count": 63449, "is_parallel": true, "self": 1110.0538563030195 }, "steps_from_proto": { "total": 109.75601361604345, "count": 63449, "is_parallel": true, "self": 22.656720485984124, "children": { "_process_rank_one_or_two_observation": { "total": 87.09929313005932, "count": 507592, "is_parallel": true, "self": 87.09929313005932 } } } } } } } } } } }, "trainer_advance": { "total": 650.0834209169689, "count": 63450, "self": 2.617431091952767, "children": { "process_trajectory": { "total": 120.79282126502017, "count": 63450, "self": 120.60044500301979, "children": { "RLTrainer._checkpoint": { "total": 0.19237626200037994, "count": 2, "self": 0.19237626200037994 } } }, "_update_policy": { "total": 526.6731685599959, "count": 445, "self": 294.5492278100203, "children": { "TorchPPOOptimizer.update": { "total": 232.12394074997565, "count": 22851, "self": 232.12394074997565 } } } } } } }, "trainer_threads": { "total": 1.3019998732488602e-06, "count": 1, "self": 1.3019998732488602e-06 }, "TrainerController._save_models": { "total": 0.07587698300039847, "count": 1, "self": 0.0010460390003572684, "children": { "RLTrainer._checkpoint": { "total": 0.0748309440000412, "count": 1, "self": 0.0748309440000412 } } } } } } }