{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2902224361896515, "min": 0.2902224361896515, "max": 1.4308667182922363, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8725.2470703125, "min": 8725.2470703125, "max": 43406.7734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989918.0, "min": 29914.0, "max": 989918.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989918.0, "min": 29914.0, "max": 989918.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5846595168113708, "min": -0.1033773422241211, "max": 0.6674125790596008, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.7813720703125, "min": -24.810562133789062, "max": 192.88223266601562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0010266407625749707, "min": -0.0020182437729090452, "max": 0.20639175176620483, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.28232622146606445, "min": -0.5610717535018921, "max": 48.91484451293945, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.09363031717090317, "min": 0.09363031717090317, "max": 0.10374818832999626, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 2.5280185636143857, "min": 1.430729675958924, "max": 2.9049492732398954, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013372513011161522, "min": 0.0007349745562113677, "max": 0.015197430044851743, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.3610578513013611, "min": 0.011024618343170514, "max": 0.4255280412558488, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.2509467868496299e-05, "min": 1.2509467868496299e-05, "max": 0.0004924160015168001, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00033775563244940006, "min": 0.00033775563244940006, "max": 0.010462444507511201, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250187407407409, "min": 0.10250187407407409, "max": 0.1984832, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.7675506000000003, "min": 2.7675506000000003, "max": 4.711830899999999, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002599372200000001, "min": 0.0002599372200000001, "max": 0.00984847168, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0070183049400000036, "min": 0.0070183049400000036, "max": 0.20929963111999997, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00741536682471633, "min": 0.00741536682471633, "max": 0.3038298189640045, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2002149075269699, "min": 0.2002149075269699, "max": 4.253617286682129, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 341.52222222222224, "min": 294.52884615384613, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30737.0, "min": 16841.0, "max": 33009.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5473266368938816, "min": -0.9999742455059483, "max": 1.6824349345802103, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.25939732044935, "min": -30.999201610684395, "max": 173.29079826176167, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5473266368938816, "min": -0.9999742455059483, "max": 1.6824349345802103, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.25939732044935, "min": -30.999201610684395, "max": 173.29079826176167, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.026733901368182465, "min": 0.025037034812413872, "max": 5.525306522846222, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4060511231364217, "min": 2.3388883091392927, "max": 93.93021088838577, "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": "1736974952", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736977527" }, "total": 2574.775658958, "count": 1, "self": 0.7269138939996083, "children": { "run_training.setup": { "total": 0.05890321499998663, "count": 1, "self": 0.05890321499998663 }, "TrainerController.start_learning": { "total": 2573.989841849, "count": 1, "self": 1.3732338769705166, "children": { "TrainerController._reset_env": { "total": 5.338655000000017, "count": 1, "self": 5.338655000000017 }, "TrainerController.advance": { "total": 2567.1940017310294, "count": 64029, "self": 1.4372849280666742, "children": { "env_step": { "total": 1566.9064719470066, "count": 64029, "self": 1419.8887945640008, "children": { "SubprocessEnvManager._take_step": { "total": 146.21517083101872, "count": 64029, "self": 4.568490114031931, "children": { "TorchPolicy.evaluate": { "total": 141.6466807169868, "count": 62567, "self": 141.6466807169868 } } }, "workers": { "total": 0.8025065519869372, "count": 64029, "self": 0.0, "children": { "worker_root": { "total": 2569.0386029690135, "count": 64029, "is_parallel": true, "self": 1264.4627569630293, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002021218000038516, "count": 1, "is_parallel": true, "self": 0.0006214670000304068, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013997510000081093, "count": 8, "is_parallel": true, "self": 0.0013997510000081093 } } }, "UnityEnvironment.step": { "total": 0.0936380130000316, "count": 1, "is_parallel": true, "self": 0.0005894259999763563, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004065040000114095, "count": 1, "is_parallel": true, "self": 0.0004065040000114095 }, "communicator.exchange": { "total": 0.09112892400003147, "count": 1, "is_parallel": true, "self": 0.09112892400003147 }, "steps_from_proto": { "total": 0.0015131590000123651, "count": 1, "is_parallel": true, "self": 0.00032799799993199485, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011851610000803703, "count": 8, "is_parallel": true, "self": 0.0011851610000803703 } } } } } } }, "UnityEnvironment.step": { "total": 1304.5758460059842, "count": 64028, "is_parallel": true, "self": 32.95515693805328, "children": { "UnityEnvironment._generate_step_input": { "total": 22.673538332976648, "count": 64028, "is_parallel": true, "self": 22.673538332976648 }, "communicator.exchange": { "total": 1153.816953717963, "count": 64028, "is_parallel": true, "self": 1153.816953717963 }, "steps_from_proto": { "total": 95.13019701699108, "count": 64028, "is_parallel": true, "self": 19.057472522966975, "children": { "_process_rank_one_or_two_observation": { "total": 76.0727244940241, "count": 512224, "is_parallel": true, "self": 76.0727244940241 } } } } } } } } } } }, "trainer_advance": { "total": 998.8502448559564, "count": 64029, "self": 2.7684512999849176, "children": { "process_trajectory": { "total": 130.0892113859665, "count": 64029, "self": 129.8354390739666, "children": { "RLTrainer._checkpoint": { "total": 0.25377231199991, "count": 2, "self": 0.25377231199991 } } }, "_update_policy": { "total": 865.9925821700049, "count": 842, "self": 398.0198666470895, "children": { "TorchPPOOptimizer.update": { "total": 467.9727155229154, "count": 45822, "self": 467.9727155229154 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.08395029500024975, "count": 1, "self": 0.001462738000554964, "children": { "RLTrainer._checkpoint": { "total": 0.08248755699969479, "count": 1, "self": 0.08248755699969479 } } } } } } }