{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.17458771169185638, "min": 0.16894619166851044, "max": 1.3931694030761719, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5215.2841796875, "min": 5079.1982421875, "max": 42263.1875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999881.0, "min": 29952.0, "max": 2999881.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999881.0, "min": 29952.0, "max": 2999881.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7950708866119385, "min": -0.130404993891716, "max": 0.8276918530464172, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 235.3409881591797, "min": -30.905982971191406, "max": 252.44601440429688, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010070549324154854, "min": -0.018839780241250992, "max": 0.3835044205188751, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.9808826446533203, "min": -5.595414638519287, "max": 90.89054870605469, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06797949553860927, "min": 0.06377287609566261, "max": 0.07272564330053807, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9517129375405298, "min": 0.49132796429606473, "max": 1.090884649508071, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014874501522475232, "min": 4.335837443941095e-05, "max": 0.017212543924134006, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20824302131465325, "min": 0.0006070172421517532, "max": 0.24097561493787606, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5773209028309587e-06, "min": 1.5773209028309587e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2082492639633422e-05, "min": 2.2082492639633422e-05, "max": 0.0039692640769119995, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052574047619049, "min": 0.10052574047619049, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.407360366666667, "min": 1.3962282666666668, "max": 2.723088, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.252147357142878e-05, "min": 6.252147357142878e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008753006300000029, "min": 0.0008753006300000029, "max": 0.1323164912, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005590212065726519, "min": 0.005223596002906561, "max": 0.4644083082675934, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07826296985149384, "min": 0.07756803929805756, "max": 3.2508580684661865, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 244.51162790697674, "min": 209.5985401459854, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31542.0, "min": 15984.0, "max": 34397.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7407353699207306, "min": -1.0000000521540642, "max": 1.7904014450355168, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 226.29559808969498, "min": -31.992801651358604, "max": 245.2849979698658, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7407353699207306, "min": -1.0000000521540642, "max": 1.7904014450355168, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 226.29559808969498, "min": -31.992801651358604, "max": 245.2849979698658, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014060602092425913, "min": 0.012487769122908901, "max": 10.09061349183321, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8278782720153686, "min": 1.601754184172023, "max": 161.44981586933136, "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": "1710826213", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710836656" }, "total": 10443.078751941, "count": 1, "self": 0.8076931560008234, "children": { "run_training.setup": { "total": 0.09565607400008957, "count": 1, "self": 0.09565607400008957 }, "TrainerController.start_learning": { "total": 10442.175402711, "count": 1, "self": 7.064893786051471, "children": { "TrainerController._reset_env": { "total": 3.82464590099994, "count": 1, "self": 3.82464590099994 }, "TrainerController.advance": { "total": 10431.181645418948, "count": 194541, "self": 6.838314584119871, "children": { "env_step": { "total": 7157.476485585146, "count": 194541, "self": 6651.212708768951, "children": { "SubprocessEnvManager._take_step": { "total": 501.7833937410528, "count": 194541, "self": 18.960544325162573, "children": { "TorchPolicy.evaluate": { "total": 482.82284941589023, "count": 187542, "self": 482.82284941589023 } } }, "workers": { "total": 4.480383075142527, "count": 194541, "self": 0.0, "children": { "worker_root": { "total": 10423.346389980365, "count": 194541, "is_parallel": true, "self": 4324.821050088334, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008508415000051173, "count": 1, "is_parallel": true, "self": 0.005868124000244279, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026402909998068935, "count": 8, "is_parallel": true, "self": 0.0026402909998068935 } } }, "UnityEnvironment.step": { "total": 0.06245114800003648, "count": 1, "is_parallel": true, "self": 0.0007577859998946224, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003785720000450965, "count": 1, "is_parallel": true, "self": 0.0003785720000450965 }, "communicator.exchange": { "total": 0.058978315000103976, "count": 1, "is_parallel": true, "self": 0.058978315000103976 }, "steps_from_proto": { "total": 0.002336474999992788, "count": 1, "is_parallel": true, "self": 0.0004853460000049381, "children": { "_process_rank_one_or_two_observation": { "total": 0.00185112899998785, "count": 8, "is_parallel": true, "self": 0.00185112899998785 } } } } } } }, "UnityEnvironment.step": { "total": 6098.52533989203, "count": 194540, "is_parallel": true, "self": 147.92356023303364, "children": { "UnityEnvironment._generate_step_input": { "total": 94.73607568178113, "count": 194540, "is_parallel": true, "self": 94.73607568178113 }, "communicator.exchange": { "total": 5412.828517000839, "count": 194540, "is_parallel": true, "self": 5412.828517000839 }, "steps_from_proto": { "total": 443.03718697637714, "count": 194540, "is_parallel": true, "self": 101.45255958625648, "children": { "_process_rank_one_or_two_observation": { "total": 341.58462739012066, "count": 1556320, "is_parallel": true, "self": 341.58462739012066 } } } } } } } } } } }, "trainer_advance": { "total": 3266.866845249683, "count": 194541, "self": 12.765490632685214, "children": { "process_trajectory": { "total": 519.1295411820217, "count": 194541, "self": 518.4171198900242, "children": { "RLTrainer._checkpoint": { "total": 0.7124212919975434, "count": 6, "self": 0.7124212919975434 } } }, "_update_policy": { "total": 2734.971813434976, "count": 1399, "self": 1089.6705054599167, "children": { "TorchPPOOptimizer.update": { "total": 1645.3013079750592, "count": 68235, "self": 1645.3013079750592 } } } } } } }, "trainer_threads": { "total": 1.196000084746629e-06, "count": 1, "self": 1.196000084746629e-06 }, "TrainerController._save_models": { "total": 0.10421640899949125, "count": 1, "self": 0.002714451000429108, "children": { "RLTrainer._checkpoint": { "total": 0.10150195799906214, "count": 1, "self": 0.10150195799906214 } } } } } } }