{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13744264841079712, "min": 0.13345272839069366, "max": 1.3960905075073242, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4132.07568359375, "min": 3990.770263671875, "max": 42351.80078125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999921.0, "min": 29959.0, "max": 2999921.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999921.0, "min": 29959.0, "max": 2999921.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7582734227180481, "min": -0.12174791097640991, "max": 0.855431079864502, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.4489288330078, "min": -29.462993621826172, "max": 258.3401794433594, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015623633749783039, "min": -0.04447856917977333, "max": 0.44018352031707764, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.624595642089844, "min": -12.453999519348145, "max": 104.76367950439453, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681904346345603, "min": 0.06317684245836323, "max": 0.07413948836624984, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9546660848838442, "min": 0.5931159069299987, "max": 1.0803821412589647, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01683544959566107, "min": 0.00012171107944547131, "max": 0.01709078858090964, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.235696294339255, "min": 0.001582244032791127, "max": 0.2527560225154922, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.58123518724048e-06, "min": 1.58123518724048e-06, "max": 0.0002983084380638542, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2137292621366718e-05, "min": 2.2137292621366718e-05, "max": 0.004010807863064066, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052704523809523, "min": 0.10052704523809523, "max": 0.19943614583333336, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073786333333334, "min": 1.4073786333333334, "max": 2.7824264000000007, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.265181928571442e-05, "min": 6.265181928571442e-05, "max": 0.009943670968749999, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008771254700000018, "min": 0.0008771254700000018, "max": 0.13369989974000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008793232962489128, "min": 0.008256019093096256, "max": 0.49350985884666443, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1231052577495575, "min": 0.11558426916599274, "max": 3.9480788707733154, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 226.8421052631579, "min": 213.93150684931507, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30170.0, "min": 16885.0, "max": 33507.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7133164025509535, "min": -0.9998968260422829, "max": 1.7721406810242555, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 229.58439794182777, "min": -31.99640166759491, "max": 256.96039874851704, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7133164025509535, "min": -0.9998968260422829, "max": 1.7721406810242555, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 229.58439794182777, "min": -31.99640166759491, "max": 256.96039874851704, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02081945744321817, "min": 0.020071138065304694, "max": 8.901318670560917, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.789807297391235, "min": 2.5254287796851713, "max": 160.2237360700965, "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": "1782587326", "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": "1782595727" }, "total": 8401.367951289, "count": 1, "self": 0.5348075960009737, "children": { "run_training.setup": { "total": 0.0247604730002422, "count": 1, "self": 0.0247604730002422 }, "TrainerController.start_learning": { "total": 8400.808383219999, "count": 1, "self": 4.341521508727965, "children": { "TrainerController._reset_env": { "total": 2.309187371999542, "count": 1, "self": 2.309187371999542 }, "TrainerController.advance": { "total": 8394.063405479274, "count": 194863, "self": 4.567430792418236, "children": { "env_step": { "total": 6355.590473840219, "count": 194863, "self": 5855.760769715385, "children": { "SubprocessEnvManager._take_step": { "total": 497.08202127428194, "count": 194863, "self": 14.802388521059584, "children": { "TorchPolicy.evaluate": { "total": 482.27963275322236, "count": 187555, "self": 482.27963275322236 } } }, "workers": { "total": 2.7476828505514277, "count": 194863, "self": 0.0, "children": { "worker_root": { "total": 8383.629094140768, "count": 194863, "is_parallel": true, "self": 2914.8360361948708, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022362870004144497, "count": 1, "is_parallel": true, "self": 0.0007280170002559316, "children": { "_process_rank_one_or_two_observation": { "total": 0.001508270000158518, "count": 8, "is_parallel": true, "self": 0.001508270000158518 } } }, "UnityEnvironment.step": { "total": 0.059317079000720696, "count": 1, "is_parallel": true, "self": 0.0005806460012536263, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005167279996385332, "count": 1, "is_parallel": true, "self": 0.0005167279996385332 }, "communicator.exchange": { "total": 0.05621479299952625, "count": 1, "is_parallel": true, "self": 0.05621479299952625 }, "steps_from_proto": { "total": 0.0020049120003022836, "count": 1, "is_parallel": true, "self": 0.00036656700194726, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016383449983550236, "count": 8, "is_parallel": true, "self": 0.0016383449983550236 } } } } } } }, "UnityEnvironment.step": { "total": 5468.793057945897, "count": 194862, "is_parallel": true, "self": 111.71209092103527, "children": { "UnityEnvironment._generate_step_input": { "total": 77.24996252487381, "count": 194862, "is_parallel": true, "self": 77.24996252487381 }, "communicator.exchange": { "total": 4914.053575007028, "count": 194862, "is_parallel": true, "self": 4914.053575007028 }, "steps_from_proto": { "total": 365.77742949296044, "count": 194862, "is_parallel": true, "self": 74.95985925362947, "children": { "_process_rank_one_or_two_observation": { "total": 290.81757023933096, "count": 1558896, "is_parallel": true, "self": 290.81757023933096 } } } } } } } } } } }, "trainer_advance": { "total": 2033.9055008466376, "count": 194863, "self": 8.721060916965143, "children": { "process_trajectory": { "total": 373.9885390696745, "count": 194863, "self": 373.43059933567383, "children": { "RLTrainer._checkpoint": { "total": 0.5579397340006835, "count": 6, "self": 0.5579397340006835 } } }, "_update_policy": { "total": 1651.195900859998, "count": 1401, "self": 880.5685868758819, "children": { "TorchPPOOptimizer.update": { "total": 770.627313984116, "count": 68289, "self": 770.627313984116 } } } } } } }, "trainer_threads": { "total": 1.43899887916632e-06, "count": 1, "self": 1.43899887916632e-06 }, "TrainerController._save_models": { "total": 0.09426742100004049, "count": 1, "self": 0.0013150139984645648, "children": { "RLTrainer._checkpoint": { "total": 0.09295240700157592, "count": 1, "self": 0.09295240700157592 } } } } } } }