{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4579711854457855, "min": 0.4579711854457855, "max": 1.3707526922225952, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13768.4453125, "min": 13768.4453125, "max": 41583.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5580952167510986, "min": -0.11447910964488983, "max": 0.5580952167510986, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.59237670898438, "min": -27.589466094970703, "max": 154.7058563232422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.015873625874519348, "min": 0.004589409101754427, "max": 0.2668275535106659, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.396994590759277, "min": 1.1702992916107178, "max": 64.3054428100586, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06653923519308377, "min": 0.06334033769962844, "max": 0.07455073479546366, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9315492927031729, "min": 0.48955413740213255, "max": 1.082061585019498, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015357771735050266, "min": 0.0003114734438457734, "max": 0.016713839647958854, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21500880429070374, "min": 0.004360628213840827, "max": 0.24086655112720715, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.283004715221427e-06, "min": 7.283004715221427e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010196206601309997, "min": 0.00010196206601309997, "max": 0.0032605877131375, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242763571428572, "min": 0.10242763571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339869, "min": 1.3886848, "max": 2.4851142000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002525208078571428, "min": 0.0002525208078571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003535291309999999, "min": 0.003535291309999999, "max": 0.10870756375000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013798423111438751, "min": 0.013798423111438751, "max": 0.45148032903671265, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19317792356014252, "min": 0.19317792356014252, "max": 3.1603622436523438, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.02298850574715, "min": 344.9782608695652, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30365.0, "min": 15984.0, "max": 33783.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6049792948981811, "min": -1.0000000521540642, "max": 1.6186404873298694, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.63319865614176, "min": -29.804001666605473, "max": 146.49879829585552, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6049792948981811, "min": -1.0000000521540642, "max": 1.6186404873298694, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.63319865614176, "min": -29.804001666605473, "max": 146.49879829585552, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04992644239396684, "min": 0.04992644239396684, "max": 9.079943422228098, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.343600488275115, "min": 4.343600488275115, "max": 145.27909475564957, "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": "1764852820", "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": "1764855832" }, "total": 3012.157673158, "count": 1, "self": 0.7343771020000531, "children": { "run_training.setup": { "total": 0.03981624800007921, "count": 1, "self": 0.03981624800007921 }, "TrainerController.start_learning": { "total": 3011.3834798079997, "count": 1, "self": 2.203615058977448, "children": { "TrainerController._reset_env": { "total": 2.9371936610000375, "count": 1, "self": 2.9371936610000375 }, "TrainerController.advance": { "total": 3006.1766980690213, "count": 63725, "self": 2.310777778107422, "children": { "env_step": { "total": 2023.8581391239832, "count": 63725, "self": 1873.0370084668443, "children": { "SubprocessEnvManager._take_step": { "total": 149.486280046116, "count": 63725, "self": 6.387955578141373, "children": { "TorchPolicy.evaluate": { "total": 143.09832446797463, "count": 62539, "self": 143.09832446797463 } } }, "workers": { "total": 1.33485061102283, "count": 63725, "self": 0.0, "children": { "worker_root": { "total": 3003.8598082800313, "count": 63725, "is_parallel": true, "self": 1302.7788933200827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0040332130001843325, "count": 1, "is_parallel": true, "self": 0.0014401170001292485, "children": { "_process_rank_one_or_two_observation": { "total": 0.002593096000055084, "count": 8, "is_parallel": true, "self": 0.002593096000055084 } } }, "UnityEnvironment.step": { "total": 0.06657822599981955, "count": 1, "is_parallel": true, "self": 0.0006306299997049791, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005150719998709974, "count": 1, "is_parallel": true, "self": 0.0005150719998709974 }, "communicator.exchange": { "total": 0.06330806799996935, "count": 1, "is_parallel": true, "self": 0.06330806799996935 }, "steps_from_proto": { "total": 0.002124456000274222, "count": 1, "is_parallel": true, "self": 0.0003914160015483503, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017330399987258716, "count": 8, "is_parallel": true, "self": 0.0017330399987258716 } } } } } } }, "UnityEnvironment.step": { "total": 1701.0809149599486, "count": 63724, "is_parallel": true, "self": 44.064415383259075, "children": { "UnityEnvironment._generate_step_input": { "total": 30.23465077286346, "count": 63724, "is_parallel": true, "self": 30.23465077286346 }, "communicator.exchange": { "total": 1487.008677233951, "count": 63724, "is_parallel": true, "self": 1487.008677233951 }, "steps_from_proto": { "total": 139.7731715698751, "count": 63724, "is_parallel": true, "self": 29.261240774055295, "children": { "_process_rank_one_or_two_observation": { "total": 110.51193079581981, "count": 509792, "is_parallel": true, "self": 110.51193079581981 } } } } } } } } } } }, "trainer_advance": { "total": 980.0077811669307, "count": 63725, "self": 4.140712278975116, "children": { "process_trajectory": { "total": 148.48261430695175, "count": 63725, "self": 148.2356666159517, "children": { "RLTrainer._checkpoint": { "total": 0.24694769100005942, "count": 2, "self": 0.24694769100005942 } } }, "_update_policy": { "total": 827.3844545810039, "count": 446, "self": 333.3306803440014, "children": { "TorchPPOOptimizer.update": { "total": 494.0537742370025, "count": 22734, "self": 494.0537742370025 } } } } } } }, "trainer_threads": { "total": 1.085000803868752e-06, "count": 1, "self": 1.085000803868752e-06 }, "TrainerController._save_models": { "total": 0.06597193400011747, "count": 1, "self": 0.0016595759998381254, "children": { "RLTrainer._checkpoint": { "total": 0.06431235800027935, "count": 1, "self": 0.06431235800027935 } } } } } } }