{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.31846556067466736, "min": 0.31846556067466736, "max": 1.3817007541656494, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9569.2529296875, "min": 9569.2529296875, "max": 41915.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5406977534294128, "min": -0.09537798911333084, "max": 0.5962140560150146, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.77328491210938, "min": -22.986095428466797, "max": 169.32479858398438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010688570328056812, "min": -0.012187344953417778, "max": 0.4032115638256073, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9607338905334473, "min": -3.4612059593200684, "max": 95.56114196777344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0672231513471589, "min": 0.06372526385807543, "max": 0.0723633754284138, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9411241188602245, "min": 0.5039319729308019, "max": 1.050389637685536, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016937730233640803, "min": 0.0004372813398665553, "max": 0.01838251245118001, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23712822327097122, "min": 0.0056846574182652185, "max": 0.25735517431652016, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.543768914014282e-06, "min": 7.543768914014282e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010561276479619995, "min": 0.00010561276479619995, "max": 0.0036328000890666996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251455714285715, "min": 0.10251455714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352038, "min": 1.3886848, "max": 2.6109333000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026120425857142844, "min": 0.00026120425857142844, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036568596199999985, "min": 0.0036568596199999985, "max": 0.12111223667, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010943783447146416, "min": 0.010943783447146416, "max": 0.5490490198135376, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15321296453475952, "min": 0.15321296453475952, "max": 3.8433432579040527, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 342.6511627906977, "min": 327.69565217391306, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29468.0, "min": 15984.0, "max": 32789.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5654650931788046, "min": -1.0000000521540642, "max": 1.673430083099232, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.6299980133772, "min": -29.93940168619156, "max": 155.62899772822857, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5654650931788046, "min": -1.0000000521540642, "max": 1.673430083099232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.6299980133772, "min": -29.93940168619156, "max": 155.62899772822857, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03878952356950152, "min": 0.03761110868654214, "max": 11.681655677035451, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.335899026977131, "min": 3.335899026977131, "max": 186.90649083256721, "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": "1745270378", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1745272560" }, "total": 2181.4618337709994, "count": 1, "self": 0.5271488459998181, "children": { "run_training.setup": { "total": 0.020123670999964816, "count": 1, "self": 0.020123670999964816 }, "TrainerController.start_learning": { "total": 2180.9145612539996, "count": 1, "self": 1.3218038500390321, "children": { "TrainerController._reset_env": { "total": 2.2610431389998666, "count": 1, "self": 2.2610431389998666 }, "TrainerController.advance": { "total": 2177.246075060961, "count": 63887, "self": 1.3511308050869957, "children": { "env_step": { "total": 1508.3735628829227, "count": 63887, "self": 1360.0666284190597, "children": { "SubprocessEnvManager._take_step": { "total": 147.5615715178892, "count": 63887, "self": 4.435002448873547, "children": { "TorchPolicy.evaluate": { "total": 143.12656906901566, "count": 62578, "self": 143.12656906901566 } } }, "workers": { "total": 0.7453629459737385, "count": 63887, "self": 0.0, "children": { "worker_root": { "total": 2176.302033749028, "count": 63887, "is_parallel": true, "self": 924.0088898730442, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00216054400016219, "count": 1, "is_parallel": true, "self": 0.0007318599991776864, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014286840009845037, "count": 8, "is_parallel": true, "self": 0.0014286840009845037 } } }, "UnityEnvironment.step": { "total": 0.07927380699993591, "count": 1, "is_parallel": true, "self": 0.0005174859998078318, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000479335999898467, "count": 1, "is_parallel": true, "self": 0.000479335999898467 }, "communicator.exchange": { "total": 0.07683765000001586, "count": 1, "is_parallel": true, "self": 0.07683765000001586 }, "steps_from_proto": { "total": 0.0014393350002137595, "count": 1, "is_parallel": true, "self": 0.00028652900027736905, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011528059999363904, "count": 8, "is_parallel": true, "self": 0.0011528059999363904 } } } } } } }, "UnityEnvironment.step": { "total": 1252.2931438759838, "count": 63886, "is_parallel": true, "self": 30.808654847958678, "children": { "UnityEnvironment._generate_step_input": { "total": 23.08572687607557, "count": 63886, "is_parallel": true, "self": 23.08572687607557 }, "communicator.exchange": { "total": 1107.2889266159332, "count": 63886, "is_parallel": true, "self": 1107.2889266159332 }, "steps_from_proto": { "total": 91.10983553601636, "count": 63886, "is_parallel": true, "self": 18.01410276767683, "children": { "_process_rank_one_or_two_observation": { "total": 73.09573276833953, "count": 511088, "is_parallel": true, "self": 73.09573276833953 } } } } } } } } } } }, "trainer_advance": { "total": 667.5213813729515, "count": 63887, "self": 2.5557372729249437, "children": { "process_trajectory": { "total": 124.73285876103228, "count": 63887, "self": 124.53772026503202, "children": { "RLTrainer._checkpoint": { "total": 0.19513849600025424, "count": 2, "self": 0.19513849600025424 } } }, "_update_policy": { "total": 540.2327853389943, "count": 455, "self": 297.5744252670297, "children": { "TorchPPOOptimizer.update": { "total": 242.65836007196458, "count": 22812, "self": 242.65836007196458 } } } } } } }, "trainer_threads": { "total": 7.930002539069392e-07, "count": 1, "self": 7.930002539069392e-07 }, "TrainerController._save_models": { "total": 0.08563841099930869, "count": 1, "self": 0.0012555649991554674, "children": { "RLTrainer._checkpoint": { "total": 0.08438284600015322, "count": 1, "self": 0.08438284600015322 } } } } } } }