{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6788015365600586, "min": 0.6584268808364868, "max": 1.430067777633667, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20548.6796875, "min": 19573.71484375, "max": 43382.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22044672071933746, "min": -0.1042863130569458, "max": 0.22044672071933746, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.43436050415039, "min": -25.028715133666992, "max": 56.43436050415039, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13427922129631042, "min": -0.008350392803549767, "max": 0.5738222002983093, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 34.37548065185547, "min": -2.1042990684509277, "max": 135.99586486816406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06644048417803601, "min": 0.06420781042447042, "max": 0.07488525516582367, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9301667784925041, "min": 0.5111314987667753, "max": 1.0483935723215314, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012587026887788035, "min": 6.051200245067871e-05, "max": 0.013551025983210578, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17621837642903249, "min": 0.0007866560318588232, "max": 0.1897143637649481, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.770997409699998e-06, "min": 7.770997409699998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010879396373579997, "min": 0.00010879396373579997, "max": 0.0033817499727500995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10259030000000001, "min": 0.10259030000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362642, "min": 1.3691136000000002, "max": 2.5272498999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026877096999999996, "min": 0.00026877096999999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037627935799999994, "min": 0.0037627935799999994, "max": 0.11275226500999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010249127633869648, "min": 0.009904943406581879, "max": 0.45586416125297546, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14348778128623962, "min": 0.1386692076921463, "max": 3.191049098968506, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 630.1020408163265, "min": 601.9166666666666, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30875.0, "min": 15984.0, "max": 33029.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8391469041911923, "min": -1.0000000521540642, "max": 0.8639813574940659, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 41.11819830536842, "min": -32.000001668930054, "max": 41.11819830536842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8391469041911923, "min": -1.0000000521540642, "max": 0.8639813574940659, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 41.11819830536842, "min": -32.000001668930054, "max": 41.11819830536842, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0664938372794161, "min": 0.0622650050354423, "max": 9.697507862001657, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.258198026691389, "min": 2.9887202417012304, "max": 155.16012579202652, "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": "1740152209", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740154307" }, "total": 2098.096080585, "count": 1, "self": 0.4927201700002115, "children": { "run_training.setup": { "total": 0.023352027000044018, "count": 1, "self": 0.023352027000044018 }, "TrainerController.start_learning": { "total": 2097.580008388, "count": 1, "self": 1.4969150109282054, "children": { "TrainerController._reset_env": { "total": 3.653614986999969, "count": 1, "self": 3.653614986999969 }, "TrainerController.advance": { "total": 2092.3330233940715, "count": 63246, "self": 1.5052409660947887, "children": { "env_step": { "total": 1399.5210020489662, "count": 63246, "self": 1232.427429790047, "children": { "SubprocessEnvManager._take_step": { "total": 166.223349784962, "count": 63246, "self": 4.936128756991309, "children": { "TorchPolicy.evaluate": { "total": 161.2872210279707, "count": 62576, "self": 161.2872210279707 } } }, "workers": { "total": 0.870222473957142, "count": 63246, "self": 0.0, "children": { "worker_root": { "total": 2092.46072918605, "count": 63246, "is_parallel": true, "self": 979.2175691410607, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006457656999998562, "count": 1, "is_parallel": true, "self": 0.004116666000015812, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023409909999827505, "count": 8, "is_parallel": true, "self": 0.0023409909999827505 } } }, "UnityEnvironment.step": { "total": 0.05683363200000713, "count": 1, "is_parallel": true, "self": 0.0005793320000293534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005194469999878493, "count": 1, "is_parallel": true, "self": 0.0005194469999878493 }, "communicator.exchange": { "total": 0.0538441139999577, "count": 1, "is_parallel": true, "self": 0.0538441139999577 }, "steps_from_proto": { "total": 0.0018907390000322266, "count": 1, "is_parallel": true, "self": 0.0005183600000577826, "children": { "_process_rank_one_or_two_observation": { "total": 0.001372378999974444, "count": 8, "is_parallel": true, "self": 0.001372378999974444 } } } } } } }, "UnityEnvironment.step": { "total": 1113.243160044989, "count": 63245, "is_parallel": true, "self": 33.07225994902137, "children": { "UnityEnvironment._generate_step_input": { "total": 23.881280706992072, "count": 63245, "is_parallel": true, "self": 23.881280706992072 }, "communicator.exchange": { "total": 956.4821729009911, "count": 63245, "is_parallel": true, "self": 956.4821729009911 }, "steps_from_proto": { "total": 99.80744648798452, "count": 63245, "is_parallel": true, "self": 20.355389210076396, "children": { "_process_rank_one_or_two_observation": { "total": 79.45205727790812, "count": 505960, "is_parallel": true, "self": 79.45205727790812 } } } } } } } } } } }, "trainer_advance": { "total": 691.3067803790104, "count": 63246, "self": 2.762860774960018, "children": { "process_trajectory": { "total": 131.13785808005247, "count": 63246, "self": 130.89114265505242, "children": { "RLTrainer._checkpoint": { "total": 0.24671542500004762, "count": 2, "self": 0.24671542500004762 } } }, "_update_policy": { "total": 557.406061523998, "count": 432, "self": 307.1504892280028, "children": { "TorchPPOOptimizer.update": { "total": 250.2555722959952, "count": 22812, "self": 250.2555722959952 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.09645399600003657, "count": 1, "self": 0.0015225379997900745, "children": { "RLTrainer._checkpoint": { "total": 0.0949314580002465, "count": 1, "self": 0.0949314580002465 } } } } } } }