{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13832613825798035, "min": 0.12418012320995331, "max": 1.3508172035217285, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4138.71826171875, "min": 3683.67919921875, "max": 35859.7890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999950.0, "min": 29952.0, "max": 2999950.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999950.0, "min": 29952.0, "max": 2999950.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6592182517051697, "min": -0.12745456397533417, "max": 0.706928551197052, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.24032592773438, "min": -30.844005584716797, "max": 202.15638732910156, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002320734318345785, "min": -0.028182102367281914, "max": 0.3238280713558197, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6521263122558594, "min": -7.411892890930176, "max": 51.56763458251953, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0705308790268069, "min": 0.06338487087309154, "max": 0.07557934604657565, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0579631854021034, "min": 0.06692438007060748, "max": 1.07577861600051, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013760651055011239, "min": 0.0004641412990070594, "max": 0.016051024975143775, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2064097658251686, "min": 0.0009150473579211393, "max": 0.22471434965201284, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5000795000066674e-06, "min": 1.5000795000066674e-06, "max": 0.0002971712009429334, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.250119250010001e-05, "min": 2.250119250010001e-05, "max": 0.0036851828716057333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049999333333334, "min": 0.10049999333333334, "max": 0.19905706666666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5074999000000002, "min": 0.19905706666666667, "max": 2.7225501000000003, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 3.494966733333335e-05, "min": 3.494966733333335e-05, "max": 0.004952947626666667, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0005242450100000002, "min": 0.0005242450100000002, "max": 0.061426873906666665, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004806843586266041, "min": 0.0044507780112326145, "max": 0.1813996434211731, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07210265100002289, "min": 0.06231088936328888, "max": 1.1462092399597168, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 300.16161616161617, "min": 266.4056603773585, "max": 997.09375, "count": 99 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29716.0, "min": 19393.0, "max": 32693.0, "count": 99 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6387224322070881, "min": -0.9354688031598926, "max": 1.7103055381664523, "count": 99 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 160.59479835629463, "min": -29.935001701116562, "max": 184.71299812197685, "count": 99 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6387224322070881, "min": -0.9354688031598926, "max": 1.7103055381664523, "count": 99 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 160.59479835629463, "min": -29.935001701116562, "max": 184.71299812197685, "count": 99 }, "Pyramids.Policy.RndReward.mean": { "value": 0.007698663292771647, "min": 0.006926339085592465, "max": 0.8143368796445429, "count": 99 }, "Pyramids.Policy.RndReward.sum": { "value": 0.7544690026916214, "min": 0.6880427094438346, "max": 26.058780148625374, "count": 99 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790150410", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "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": "1790155395" }, "total": 4985.166659363999, "count": 1, "self": 0.32217134199891007, "children": { "run_training.setup": { "total": 0.01905753499988805, "count": 1, "self": 0.01905753499988805 }, "TrainerController.start_learning": { "total": 4984.825430487001, "count": 1, "self": 4.103840898023918, "children": { "TrainerController._reset_env": { "total": 2.1530006820000835, "count": 1, "self": 2.1530006820000835 }, "TrainerController.advance": { "total": 4978.4920013289775, "count": 191661, "self": 4.102447820310772, "children": { "env_step": { "total": 3187.4414579767554, "count": 191661, "self": 2765.419254809788, "children": { "SubprocessEnvManager._take_step": { "total": 419.52347436694185, "count": 191661, "self": 12.83378418395182, "children": { "TorchPolicy.evaluate": { "total": 406.68969018299003, "count": 186056, "self": 406.68969018299003 } } }, "workers": { "total": 2.498728800025333, "count": 191661, "self": 0.0, "children": { "worker_root": { "total": 4978.32524243805, "count": 191661, "is_parallel": true, "self": 2485.9456943289824, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001756358000079672, "count": 1, "is_parallel": true, "self": 0.0005704040000864552, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011859539999932167, "count": 8, "is_parallel": true, "self": 0.0011859539999932167 } } }, "UnityEnvironment.step": { "total": 0.037690768000061325, "count": 1, "is_parallel": true, "self": 0.0003741660001423952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002916809999078396, "count": 1, "is_parallel": true, "self": 0.0002916809999078396 }, "communicator.exchange": { "total": 0.03599274900000182, "count": 1, "is_parallel": true, "self": 0.03599274900000182 }, "steps_from_proto": { "total": 0.0010321720000092682, "count": 1, "is_parallel": true, "self": 0.00023440300003585435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007977689999734139, "count": 8, "is_parallel": true, "self": 0.0007977689999734139 } } } } } } }, "UnityEnvironment.step": { "total": 2492.3795481090674, "count": 191660, "is_parallel": true, "self": 58.02117656398286, "children": { "UnityEnvironment._generate_step_input": { "total": 39.068643469009885, "count": 191660, "is_parallel": true, "self": 39.068643469009885 }, "communicator.exchange": { "total": 2221.24984525119, "count": 191660, "is_parallel": true, "self": 2221.24984525119 }, "steps_from_proto": { "total": 174.03988282488478, "count": 191660, "is_parallel": true, "self": 37.74017411931379, "children": { "_process_rank_one_or_two_observation": { "total": 136.299708705571, "count": 1533280, "is_parallel": true, "self": 136.299708705571 } } } } } } } } } } }, "trainer_advance": { "total": 1786.9480955319113, "count": 191661, "self": 8.143545214779351, "children": { "process_trajectory": { "total": 316.90058247613126, "count": 191661, "self": 316.42374752913213, "children": { "RLTrainer._checkpoint": { "total": 0.47683494699913354, "count": 6, "self": 0.47683494699913354 } } }, "_update_policy": { "total": 1461.9039678410008, "count": 1383, "self": 786.3477572070248, "children": { "TorchPPOOptimizer.update": { "total": 675.5562106339761, "count": 67815, "self": 675.5562106339761 } } } } } } }, "trainer_threads": { "total": 1.1329993867548183e-06, "count": 1, "self": 1.1329993867548183e-06 }, "TrainerController._save_models": { "total": 0.07658644499952061, "count": 1, "self": 0.0013299999991431832, "children": { "RLTrainer._checkpoint": { "total": 0.07525644500037743, "count": 1, "self": 0.07525644500037743 } } } } } } }