{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3237864375114441, "min": 0.31810370087623596, "max": 1.588344931602478, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3310.392578125, "min": 3119.961181640625, "max": 16264.65234375, "count": 100 }, "Pyramids.Step.mean": { "value": 999945.0, "min": 9984.0, "max": 999945.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999945.0, "min": 9984.0, "max": 999945.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4371621310710907, "min": -0.14251695573329926, "max": 0.7079083919525146, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 38.90742874145508, "min": -11.11632251739502, "max": 65.12757110595703, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011771360412240028, "min": 0.000479597772937268, "max": 0.4647774398326874, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.0476510524749756, "min": 0.0422046035528183, "max": 36.25263977050781, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07231817814366272, "min": 0.06107394570911613, "max": 0.07849415072679049, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.3615908907183136, "min": 0.14153848851371245, "max": 0.37971370184095576, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010330927182803862, "min": 0.00015641979250648712, "max": 0.01931714837216229, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.051654635914019316, "min": 0.0006256791700259485, "max": 0.0898490241910194, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.6335994554999963e-06, "min": 1.6335994554999963e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.167997277499981e-06, "min": 8.167997277499981e-06, "max": 0.0013125621624793002, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10054450000000001, "min": 0.10054450000000001, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5027225000000001, "min": 0.39717119999999995, "max": 0.9375207000000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.439554999999989e-05, "min": 6.439554999999989e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003219777499999994, "min": 0.0003219777499999994, "max": 0.04375831793, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010893860831856728, "min": 0.01076428685337305, "max": 0.8226414918899536, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05446930602192879, "min": 0.0430571474134922, "max": 1.6452829837799072, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 403.4, "min": 309.84375, "max": 999.0, "count": 98 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 8068.0, "min": 999.0, "max": 16202.0, "count": 98 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4825684036079205, "min": -1.0000000521540642, "max": 1.6639999449253082, "count": 98 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 28.16879966855049, "min": -16.000000834465027, "max": 50.084399193525314, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4825684036079205, "min": -1.0000000521540642, "max": 1.6639999449253082, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 28.16879966855049, "min": -16.000000834465027, "max": 50.084399193525314, "count": 98 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04826814494414353, "min": 0.03412850837587569, "max": 9.804138541221619, "count": 98 }, "Pyramids.Policy.RndReward.sum": { "value": 0.9170947539387271, "min": 0.17582036554813385, "max": 156.8662166595459, "count": 98 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1762757995", "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": "1762760323" }, "total": 2327.7597867570003, "count": 1, "self": 1.2822127410004214, "children": { "run_training.setup": { "total": 0.04767040199976691, "count": 1, "self": 0.04767040199976691 }, "TrainerController.start_learning": { "total": 2326.429903614, "count": 1, "self": 1.4031294270421313, "children": { "TrainerController._reset_env": { "total": 5.235476812999877, "count": 1, "self": 5.235476812999877 }, "TrainerController.advance": { "total": 2319.5879654469577, "count": 63892, "self": 1.4390108628517737, "children": { "env_step": { "total": 1623.6819257289376, "count": 63892, "self": 1467.5186215640174, "children": { "SubprocessEnvManager._take_step": { "total": 155.3370998918872, "count": 63892, "self": 4.812713019759485, "children": { "TorchPolicy.evaluate": { "total": 150.5243868721277, "count": 62565, "self": 150.5243868721277 } } }, "workers": { "total": 0.8262042730329995, "count": 63892, "self": 0.0, "children": { "worker_root": { "total": 2317.2171337280147, "count": 63892, "is_parallel": true, "self": 976.5192746710459, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018245890000798681, "count": 1, "is_parallel": true, "self": 0.0005894280002394225, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012351609998404456, "count": 8, "is_parallel": true, "self": 0.0012351609998404456 } } }, "UnityEnvironment.step": { "total": 0.049218402999940736, "count": 1, "is_parallel": true, "self": 0.0005375400000957598, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045722799995928654, "count": 1, "is_parallel": true, "self": 0.00045722799995928654 }, "communicator.exchange": { "total": 0.0463869209997938, "count": 1, "is_parallel": true, "self": 0.0463869209997938 }, "steps_from_proto": { "total": 0.001836714000091888, "count": 1, "is_parallel": true, "self": 0.0003844890002255852, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014522249998663028, "count": 8, "is_parallel": true, "self": 0.0014522249998663028 } } } } } } }, "UnityEnvironment.step": { "total": 1340.6978590569688, "count": 63891, "is_parallel": true, "self": 34.071416558218516, "children": { "UnityEnvironment._generate_step_input": { "total": 22.98546979493267, "count": 63891, "is_parallel": true, "self": 22.98546979493267 }, "communicator.exchange": { "total": 1170.5119343989454, "count": 63891, "is_parallel": true, "self": 1170.5119343989454 }, "steps_from_proto": { "total": 113.12903830487221, "count": 63891, "is_parallel": true, "self": 24.451759901785863, "children": { "_process_rank_one_or_two_observation": { "total": 88.67727840308635, "count": 511128, "is_parallel": true, "self": 88.67727840308635 } } } } } } } } } } }, "trainer_advance": { "total": 694.4670288551683, "count": 63892, "self": 2.643223672091608, "children": { "process_trajectory": { "total": 138.0346776260776, "count": 63892, "self": 137.63955811807682, "children": { "RLTrainer._checkpoint": { "total": 0.3951195080007892, "count": 2, "self": 0.3951195080007892 } } }, "_update_policy": { "total": 553.7891275569991, "count": 451, "self": 310.42613398599724, "children": { "TorchPPOOptimizer.update": { "total": 243.36299357100188, "count": 22800, "self": 243.36299357100188 } } } } } } }, "trainer_threads": { "total": 1.4470006135525182e-06, "count": 1, "self": 1.4470006135525182e-06 }, "TrainerController._save_models": { "total": 0.2033304799997495, "count": 1, "self": 0.037743167000371614, "children": { "RLTrainer._checkpoint": { "total": 0.1655873129993779, "count": 1, "self": 0.1655873129993779 } } } } } } }