{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4076777994632721, "min": 0.4076777994632721, "max": 1.4934115409851074, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 12184.673828125, "min": 12184.673828125, "max": 45304.1328125, "count": 40 }, "Pyramids.Step.mean": { "value": 1199883.0, "min": 29952.0, "max": 1199883.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199883.0, "min": 29952.0, "max": 1199883.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6954107880592346, "min": -0.09742878377437592, "max": 0.6994468569755554, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 200.27830505371094, "min": -23.480337142944336, "max": 204.2384796142578, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01983293890953064, "min": -0.004198300186544657, "max": 0.1148994043469429, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.711886405944824, "min": -1.1839206218719482, "max": 27.69075584411621, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06802041761587564, "min": 0.06637534774313289, "max": 0.0727891651765331, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.952285846622259, "min": 0.48857434590640825, "max": 1.0848184567856187, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0156220121995017, "min": 0.00034115495917652237, "max": 0.016226465562875894, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2187081707930238, "min": 0.004681720368464584, "max": 0.24339698344313843, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00018156988947671664, "min": 0.00018156988947671664, "max": 0.00029838354339596195, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002541978452674033, "min": 0.0020886848037717336, "max": 0.0039690878769707335, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16052328333333335, "min": 0.16052328333333335, "max": 0.19946118095238097, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2473259666666667, "min": 1.3962282666666668, "max": 2.7825642666666672, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.006056276005000001, "min": 0.006056276005000001, "max": 0.009946171977142856, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.08478786407000001, "min": 0.06962320384, "max": 0.13231062374, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007146864198148251, "min": 0.006534443702548742, "max": 0.26361268758773804, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10005609691143036, "min": 0.09465163201093674, "max": 1.8452887535095215, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 265.0353982300885, "min": 265.0353982300885, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29949.0, "min": 15984.0, "max": 33694.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6995557338922425, "min": -1.0000000521540642, "max": 1.7216074600397984, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.0497979298234, "min": -30.568401664495468, "max": 192.0497979298234, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6995557338922425, "min": -1.0000000521540642, "max": 1.7216074600397984, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.0497979298234, "min": -30.568401664495468, "max": 192.0497979298234, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01957071450331858, "min": 0.01957071450331858, "max": 5.099649786017835, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.211490738875, "min": 1.9885592649079626, "max": 81.59439657628536, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727296696", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727300714" }, "total": 4017.994968448, "count": 1, "self": 0.45666657399988253, "children": { "run_training.setup": { "total": 0.07944490299996687, "count": 1, "self": 0.07944490299996687 }, "TrainerController.start_learning": { "total": 4017.458856971, "count": 1, "self": 2.9395994289698137, "children": { "TrainerController._reset_env": { "total": 2.4107611660001567, "count": 1, "self": 2.4107611660001567 }, "TrainerController.advance": { "total": 4011.97823404003, "count": 76658, "self": 3.0661805230197388, "children": { "env_step": { "total": 2640.799717730005, "count": 76658, "self": 2434.0475942079192, "children": { "SubprocessEnvManager._take_step": { "total": 205.063612652159, "count": 76658, "self": 8.690300779105883, "children": { "TorchPolicy.evaluate": { "total": 196.37331187305313, "count": 75073, "self": 196.37331187305313 } } }, "workers": { "total": 1.6885108699264038, "count": 76658, "self": 0.0, "children": { "worker_root": { "total": 4007.5002256029725, "count": 76658, "is_parallel": true, "self": 1798.3718893020118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003245567000021765, "count": 1, "is_parallel": true, "self": 0.0011665480001283868, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020790189998933783, "count": 8, "is_parallel": true, "self": 0.0020790189998933783 } } }, "UnityEnvironment.step": { "total": 0.06835669499992036, "count": 1, "is_parallel": true, "self": 0.0007596229997943738, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005325260001427523, "count": 1, "is_parallel": true, "self": 0.0005325260001427523 }, "communicator.exchange": { "total": 0.06479261900017264, "count": 1, "is_parallel": true, "self": 0.06479261900017264 }, "steps_from_proto": { "total": 0.002271926999810603, "count": 1, "is_parallel": true, "self": 0.0006308740003078128, "children": { "_process_rank_one_or_two_observation": { "total": 0.00164105299950279, "count": 8, "is_parallel": true, "self": 0.00164105299950279 } } } } } } }, "UnityEnvironment.step": { "total": 2209.1283363009607, "count": 76657, "is_parallel": true, "self": 60.207307868024145, "children": { "UnityEnvironment._generate_step_input": { "total": 37.58462842998688, "count": 76657, "is_parallel": true, "self": 37.58462842998688 }, "communicator.exchange": { "total": 1954.1755094959294, "count": 76657, "is_parallel": true, "self": 1954.1755094959294 }, "steps_from_proto": { "total": 157.16089050701999, "count": 76657, "is_parallel": true, "self": 34.21555519283788, "children": { "_process_rank_one_or_two_observation": { "total": 122.9453353141821, "count": 613256, "is_parallel": true, "self": 122.9453353141821 } } } } } } } } } } }, "trainer_advance": { "total": 1368.1123357870056, "count": 76658, "self": 5.877730106011995, "children": { "process_trajectory": { "total": 204.43068953500097, "count": 76658, "self": 204.24447860900136, "children": { "RLTrainer._checkpoint": { "total": 0.1862109259996032, "count": 2, "self": 0.1862109259996032 } } }, "_update_policy": { "total": 1157.8039161459926, "count": 545, "self": 461.59943387495264, "children": { "TorchPPOOptimizer.update": { "total": 696.20448227104, "count": 27373, "self": 696.20448227104 } } } } } } }, "trainer_threads": { "total": 2.337999831070192e-06, "count": 1, "self": 2.337999831070192e-06 }, "TrainerController._save_models": { "total": 0.1302599979999286, "count": 1, "self": 0.0029422309999063145, "children": { "RLTrainer._checkpoint": { "total": 0.12731776700002229, "count": 1, "self": 0.12731776700002229 } } } } } } }