{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43157386779785156, "min": 0.43157386779785156, "max": 1.1835137605667114, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12954.12109375, "min": 12954.12109375, "max": 33916.4375, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6525560021400452, "min": -0.19506368041038513, "max": 0.6525560021400452, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.32589721679688, "min": -26.498668670654297, "max": 185.32589721679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.018126411363482475, "min": -0.032225046306848526, "max": 0.47743427753448486, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.1479010581970215, "min": -8.86188793182373, "max": 86.08393859863281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07054435086964188, "min": 0.06523563337072523, "max": 0.0744501472680565, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9876209121749863, "min": 0.1957069001121757, "max": 1.0574157290102448, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015353312257278501, "min": 0.0007061740459281193, "max": 0.01610820238004505, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21494637160189903, "min": 0.008058103971658662, "max": 0.2255148333206307, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.751711701842858e-06, "min": 7.751711701842858e-06, "max": 0.00029274240241920004, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010852396382580002, "min": 0.00010852396382580002, "max": 0.0036326677891107993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258387142857142, "min": 0.10258387142857142, "max": 0.19758080000000003, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361742, "min": 0.5927424000000001, "max": 2.6108892000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026812875571428576, "min": 0.00026812875571428576, "max": 0.00975832192, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037538025800000004, "min": 0.0037538025800000004, "max": 0.12110783107999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01063509937375784, "min": 0.010519095696508884, "max": 0.2793361246585846, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1488913893699646, "min": 0.14726734161376953, "max": 1.2707055807113647, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.45631067961165, "min": 299.45631067961165, "max": 999.0, "count": 32 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30844.0, "min": 24318.0, "max": 33372.0, "count": 32 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6798764544666982, "min": -1.0000000521540642, "max": 1.6798764544666982, "count": 32 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.34739835560322, "min": -32.000001668930054, "max": 171.34739835560322, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6798764544666982, "min": -1.0000000521540642, "max": 1.6798764544666982, "count": 32 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.34739835560322, "min": -32.000001668930054, "max": 171.34739835560322, "count": 32 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03312544703201674, "min": 0.03312544703201674, "max": 2.579658311791718, "count": 32 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3787955972657073, "min": 3.065735498068534, "max": 82.54906597733498, "count": 32 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1751406869", "python_version": "3.10.18 (main, Jun 4 2025, 08:56:00) [GCC 13.3.0]", "command_line_arguments": "/home/cogollo/mlagents_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751408842" }, "total": 1856.999686985997, "count": 1, "self": 0.31932419499207754, "children": { "run_training.setup": { "total": 0.021418308999272995, "count": 1, "self": 0.021418308999272995 }, "TrainerController.start_learning": { "total": 1856.6589444820056, "count": 1, "self": 1.2493460242112633, "children": { "TrainerController._reset_env": { "total": 2.5361245889944257, "count": 1, "self": 2.5361245889944257 }, "TrainerController.advance": { "total": 1852.7811810717976, "count": 63022, "self": 1.1899232625946752, "children": { "env_step": { "total": 1042.043702635463, "count": 63022, "self": 779.9959552165164, "children": { "SubprocessEnvManager._take_step": { "total": 261.22081486089155, "count": 63022, "self": 4.396588633302599, "children": { "TorchPolicy.evaluate": { "total": 256.82422622758895, "count": 61558, "self": 256.82422622758895 } } }, "workers": { "total": 0.8269325580549776, "count": 63022, "self": 0.0, "children": { "worker_root": { "total": 1854.0195414528062, "count": 63022, "is_parallel": true, "self": 1156.042825190416, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018153179989894852, "count": 1, "is_parallel": true, "self": 0.0007114139953046106, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011039040036848746, "count": 8, "is_parallel": true, "self": 0.0011039040036848746 } } }, "UnityEnvironment.step": { "total": 0.027480443997774273, "count": 1, "is_parallel": true, "self": 0.00023723299818811938, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018620800256030634, "count": 1, "is_parallel": true, "self": 0.00018620800256030634 }, "communicator.exchange": { "total": 0.026354200999776367, "count": 1, "is_parallel": true, "self": 0.026354200999776367 }, "steps_from_proto": { "total": 0.0007028019972494803, "count": 1, "is_parallel": true, "self": 0.00017835199105320498, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005244500061962754, "count": 8, "is_parallel": true, "self": 0.0005244500061962754 } } } } } } }, "UnityEnvironment.step": { "total": 697.9767162623903, "count": 63021, "is_parallel": true, "self": 13.67834424200555, "children": { "UnityEnvironment._generate_step_input": { "total": 10.789437118080969, "count": 63021, "is_parallel": true, "self": 10.789437118080969 }, "communicator.exchange": { "total": 634.0428370539157, "count": 63021, "is_parallel": true, "self": 634.0428370539157 }, "steps_from_proto": { "total": 39.46609784838802, "count": 63021, "is_parallel": true, "self": 9.871907055916381, "children": { "_process_rank_one_or_two_observation": { "total": 29.594190792471636, "count": 504168, "is_parallel": true, "self": 29.594190792471636 } } } } } } } } } } }, "trainer_advance": { "total": 809.54755517374, "count": 63022, "self": 2.3640318971447414, "children": { "process_trajectory": { "total": 127.37807295958919, "count": 63022, "self": 127.17165255959117, "children": { "RLTrainer._checkpoint": { "total": 0.20642039999802364, "count": 2, "self": 0.20642039999802364 } } }, "_update_policy": { "total": 679.805450317006, "count": 445, "self": 277.75940190442634, "children": { "TorchPPOOptimizer.update": { "total": 402.0460484125797, "count": 22410, "self": 402.0460484125797 } } } } } } }, "trainer_threads": { "total": 6.440022843889892e-07, "count": 1, "self": 6.440022843889892e-07 }, "TrainerController._save_models": { "total": 0.0922921530000167, "count": 1, "self": 0.0020129369950154796, "children": { "RLTrainer._checkpoint": { "total": 0.09027921600500122, "count": 1, "self": 0.09027921600500122 } } } } } } }