{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32520464062690735, "min": 0.31535670161247253, "max": 1.457248568534851, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9761.3427734375, "min": 9369.8779296875, "max": 44207.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29952.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5025843381881714, "min": -0.08614015579223633, "max": 0.6407259702682495, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.1951904296875, "min": -20.67363739013672, "max": 183.24761962890625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004789841827005148, "min": -0.004789841827005148, "max": 0.3940031826496124, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.2884674072265625, "min": -1.2884674072265625, "max": 93.37875366210938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06813785973137391, "min": 0.06550749828518858, "max": 0.07385493575214963, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0220678959706087, "min": 0.4805592118900259, "max": 1.0390183342193875, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016791327607215325, "min": 0.0008191076066369108, "max": 0.017638788310120748, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2518699141082299, "min": 0.01064839888627984, "max": 0.25758750637760386, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468377510573333e-06, "min": 7.468377510573333e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001120256626586, "min": 0.0001120256626586, "max": 0.0035089997303335, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248942666666667, "min": 0.10248942666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373414, "min": 1.3886848, "max": 2.5696665000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025869372400000003, "min": 0.00025869372400000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038804058600000004, "min": 0.0038804058600000004, "max": 0.11698968335000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010202108882367611, "min": 0.010202108882367611, "max": 0.3898983299732208, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1530316323041916, "min": 0.14510056376457214, "max": 2.729288339614868, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 369.8192771084337, "min": 286.16831683168317, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30695.0, "min": 15984.0, "max": 33180.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5819807059793587, "min": -1.0000000521540642, "max": 1.6940217689417376, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.30439859628677, "min": -29.212001785635948, "max": 171.0961986631155, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5819807059793587, "min": -1.0000000521540642, "max": 1.6940217689417376, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.30439859628677, "min": -29.212001785635948, "max": 171.0961986631155, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038749201132786876, "min": 0.031909226662974105, "max": 8.113460941240191, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2161836940213107, "min": 3.1909226662974106, "max": 129.81537505984306, "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": "1785875666", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda/envs/py310/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": "1785878455" }, "total": 2788.479528731, "count": 1, "self": 0.48153139099940745, "children": { "run_training.setup": { "total": 0.02550659300004554, "count": 1, "self": 0.02550659300004554 }, "TrainerController.start_learning": { "total": 2787.9724907470004, "count": 1, "self": 1.8515873998967436, "children": { "TrainerController._reset_env": { "total": 2.236116003999996, "count": 1, "self": 2.236116003999996 }, "TrainerController.advance": { "total": 2783.7824655651034, "count": 63989, "self": 1.8973255543219238, "children": { "env_step": { "total": 2131.8010858839057, "count": 63989, "self": 1944.845993149669, "children": { "SubprocessEnvManager._take_step": { "total": 185.81003053007862, "count": 63989, "self": 5.372163832068509, "children": { "TorchPolicy.evaluate": { "total": 180.4378666980101, "count": 62553, "self": 180.4378666980101 } } }, "workers": { "total": 1.1450622041579663, "count": 63989, "self": 0.0, "children": { "worker_root": { "total": 2781.603219283919, "count": 63989, "is_parallel": true, "self": 981.6011970889363, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018763640000543091, "count": 1, "is_parallel": true, "self": 0.0006148269999357581, "children": { "_process_rank_one_or_two_observation": { "total": 0.001261537000118551, "count": 8, "is_parallel": true, "self": 0.001261537000118551 } } }, "UnityEnvironment.step": { "total": 0.05501345299990135, "count": 1, "is_parallel": true, "self": 0.0005847659999744792, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004660039999180299, "count": 1, "is_parallel": true, "self": 0.0004660039999180299 }, "communicator.exchange": { "total": 0.05217394000010245, "count": 1, "is_parallel": true, "self": 0.05217394000010245 }, "steps_from_proto": { "total": 0.0017887429999063897, "count": 1, "is_parallel": true, "self": 0.00041881500010276795, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013699279998036218, "count": 8, "is_parallel": true, "self": 0.0013699279998036218 } } } } } } }, "UnityEnvironment.step": { "total": 1800.0020221949826, "count": 63988, "is_parallel": true, "self": 37.93128819292315, "children": { "UnityEnvironment._generate_step_input": { "total": 25.922551911013215, "count": 63988, "is_parallel": true, "self": 25.922551911013215 }, "communicator.exchange": { "total": 1613.7068406760059, "count": 63988, "is_parallel": true, "self": 1613.7068406760059 }, "steps_from_proto": { "total": 122.44134141504037, "count": 63988, "is_parallel": true, "self": 26.19734068903881, "children": { "_process_rank_one_or_two_observation": { "total": 96.24400072600156, "count": 511904, "is_parallel": true, "self": 96.24400072600156 } } } } } } } } } } }, "trainer_advance": { "total": 650.0840541268758, "count": 63989, "self": 3.596871865920093, "children": { "process_trajectory": { "total": 118.65901184495897, "count": 63989, "self": 118.44512783795926, "children": { "RLTrainer._checkpoint": { "total": 0.2138840069997059, "count": 2, "self": 0.2138840069997059 } } }, "_update_policy": { "total": 527.8281704159967, "count": 454, "self": 278.3781553250301, "children": { "TorchPPOOptimizer.update": { "total": 249.45001509096664, "count": 22773, "self": 249.45001509096664 } } } } } } }, "trainer_threads": { "total": 7.990001904545352e-07, "count": 1, "self": 7.990001904545352e-07 }, "TrainerController._save_models": { "total": 0.1023209790000692, "count": 1, "self": 0.0010286699998687254, "children": { "RLTrainer._checkpoint": { "total": 0.10129230900020048, "count": 1, "self": 0.10129230900020048 } } } } } } }