{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13279588520526886, "min": 0.1276216357946396, "max": 1.5100661516189575, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3981.751953125, "min": 3843.506103515625, "max": 45809.3671875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999955.0, "min": 29952.0, "max": 2999955.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999955.0, "min": 29952.0, "max": 2999955.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7765174508094788, "min": -0.12612566351890564, "max": 0.8122166991233826, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 232.95523071289062, "min": -29.891782760620117, "max": 245.11643981933594, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00495332945138216, "min": -0.018807025626301765, "max": 0.4251170754432678, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4859988689422607, "min": -5.529265403747559, "max": 100.75274658203125, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0669019984225521, "min": 0.06402619248408535, "max": 0.07364090123179513, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9366279779157293, "min": 0.515486308622566, "max": 1.0730021896888502, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015109357492682258, "min": 0.0008536211755744702, "max": 0.01724082210369358, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2115310048975516, "min": 0.010243454106893642, "max": 0.24137150945171013, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.468999510366665e-06, "min": 1.468999510366665e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0565993145133312e-05, "min": 2.0565993145133312e-05, "max": 0.0039693559768813665, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048963333333334, "min": 0.10048963333333334, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068548666666667, "min": 1.3962282666666668, "max": 2.7674477333333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.891436999999994e-05, "min": 5.891436999999994e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008248011799999992, "min": 0.0008248011799999992, "max": 0.13231955147000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006202308926731348, "min": 0.006202308926731348, "max": 0.6022911667823792, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08683232218027115, "min": 0.08683232218027115, "max": 4.216038227081299, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 238.46153846153845, "min": 216.85384615384615, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31000.0, "min": 15984.0, "max": 32696.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7457813864299494, "min": -1.0000000521540642, "max": 1.7707822481470723, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.20579884946346, "min": -30.72800175845623, "max": 236.1653986275196, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7457813864299494, "min": -1.0000000521540642, "max": 1.7707822481470723, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.20579884946346, "min": -30.72800175845623, "max": 236.1653986275196, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015671909666397293, "min": 0.015229424077439874, "max": 12.687960926443338, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0216763469652506, "min": 1.952062553173164, "max": 203.00737482309341, "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": "1775916546", "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_env/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": "1775923911" }, "total": 7365.131160466, "count": 1, "self": 0.7075720490011008, "children": { "run_training.setup": { "total": 0.02576448799982245, "count": 1, "self": 0.02576448799982245 }, "TrainerController.start_learning": { "total": 7364.397823928999, "count": 1, "self": 4.644521037062077, "children": { "TrainerController._reset_env": { "total": 2.3667731900000035, "count": 1, "self": 2.3667731900000035 }, "TrainerController.advance": { "total": 7357.300293933937, "count": 194544, "self": 4.702609164880414, "children": { "env_step": { "total": 5312.994435509045, "count": 194544, "self": 4822.917501759671, "children": { "SubprocessEnvManager._take_step": { "total": 487.21450290226676, "count": 194544, "self": 14.572083858023689, "children": { "TorchPolicy.evaluate": { "total": 472.64241904424307, "count": 187557, "self": 472.64241904424307 } } }, "workers": { "total": 2.8624308471071345, "count": 194544, "self": 0.0, "children": { "worker_root": { "total": 7344.031394370102, "count": 194544, "is_parallel": true, "self": 2902.051859378209, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017463559997850098, "count": 1, "is_parallel": true, "self": 0.000578920999487309, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011674350002977008, "count": 8, "is_parallel": true, "self": 0.0011674350002977008 } } }, "UnityEnvironment.step": { "total": 0.05433119600002101, "count": 1, "is_parallel": true, "self": 0.0005415370001173869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046252099991761497, "count": 1, "is_parallel": true, "self": 0.00046252099991761497 }, "communicator.exchange": { "total": 0.05154338200009079, "count": 1, "is_parallel": true, "self": 0.05154338200009079 }, "steps_from_proto": { "total": 0.0017837559998952202, "count": 1, "is_parallel": true, "self": 0.0003848189999189344, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013989369999762857, "count": 8, "is_parallel": true, "self": 0.0013989369999762857 } } } } } } }, "UnityEnvironment.step": { "total": 4441.979534991893, "count": 194543, "is_parallel": true, "self": 103.544239829851, "children": { "UnityEnvironment._generate_step_input": { "total": 71.26049822862024, "count": 194543, "is_parallel": true, "self": 71.26049822862024 }, "communicator.exchange": { "total": 3930.9001369647294, "count": 194543, "is_parallel": true, "self": 3930.9001369647294 }, "steps_from_proto": { "total": 336.27465996869296, "count": 194543, "is_parallel": true, "self": 72.61463308996554, "children": { "_process_rank_one_or_two_observation": { "total": 263.6600268787274, "count": 1556344, "is_parallel": true, "self": 263.6600268787274 } } } } } } } } } } }, "trainer_advance": { "total": 2039.6032492600111, "count": 194544, "self": 9.248691783554477, "children": { "process_trajectory": { "total": 391.15998838244104, "count": 194544, "self": 390.62292449844153, "children": { "RLTrainer._checkpoint": { "total": 0.5370638839995081, "count": 6, "self": 0.5370638839995081 } } }, "_update_policy": { "total": 1639.1945690940156, "count": 1396, "self": 905.6089767299436, "children": { "TorchPPOOptimizer.update": { "total": 733.585592364072, "count": 68421, "self": 733.585592364072 } } } } } } }, "trainer_threads": { "total": 1.3030003174208105e-06, "count": 1, "self": 1.3030003174208105e-06 }, "TrainerController._save_models": { "total": 0.0862344649995066, "count": 1, "self": 0.001065538999682758, "children": { "RLTrainer._checkpoint": { "total": 0.08516892599982384, "count": 1, "self": 0.08516892599982384 } } } } } } }