{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3191472291946411, "min": 0.3057059645652771, "max": 1.3908493518829346, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9615.267578125, "min": 9127.1572265625, "max": 42192.8046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5525098443031311, "min": -0.09002811461687088, "max": 0.6763673424720764, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.12283325195312, "min": -21.78680419921875, "max": 191.41195678710938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022005505859851837, "min": -0.004445615224540234, "max": 0.47642505168914795, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.33758544921875, "min": -1.2581090927124023, "max": 112.91273498535156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0682436155994747, "min": 0.06557597851900662, "max": 0.07430821960790131, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9554106183926457, "min": 0.49749007896911934, "max": 1.0575463627014243, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.020275005826754112, "min": 0.0005918263905836543, "max": 0.020275005826754112, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.28385008157455754, "min": 0.004142784734085581, "max": 0.28385008157455754, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.53061177554286e-06, "min": 7.53061177554286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010542856485760003, "min": 0.00010542856485760003, "max": 0.0033835298721568, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251017142857144, "min": 0.10251017142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351424000000002, "min": 1.3691136000000002, "max": 2.6173256, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607661257142858, "min": 0.0002607661257142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003650725760000001, "min": 0.003650725760000001, "max": 0.11281153567999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01308396551758051, "min": 0.01308396551758051, "max": 0.46969836950302124, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18317551910877228, "min": 0.18317551910877228, "max": 3.287888526916504, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.7448979591837, "min": 284.1730769230769, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32021.0, "min": 15984.0, "max": 34282.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6114484676809022, "min": -1.0000000521540642, "max": 1.705459985435009, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.53339830040932, "min": -32.000001668930054, "max": 176.44499846547842, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6114484676809022, "min": -1.0000000521540642, "max": 1.705459985435009, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.53339830040932, "min": -32.000001668930054, "max": 176.44499846547842, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04434726943174904, "min": 0.03904319512282829, "max": 8.690058313310146, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.390379673743155, "min": 3.8511583506769966, "max": 139.04093301296234, "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": "1715733974", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715737400" }, "total": 3425.8004379920003, "count": 1, "self": 0.754805729000509, "children": { "run_training.setup": { "total": 0.09334687099999428, "count": 1, "self": 0.09334687099999428 }, "TrainerController.start_learning": { "total": 3424.952285392, "count": 1, "self": 2.165698326058191, "children": { "TrainerController._reset_env": { "total": 3.861868382999944, "count": 1, "self": 3.861868382999944 }, "TrainerController.advance": { "total": 3418.7870484169416, "count": 64015, "self": 2.4450644949261005, "children": { "env_step": { "total": 2335.8827663210245, "count": 64015, "self": 2176.385351018057, "children": { "SubprocessEnvManager._take_step": { "total": 158.09781304698936, "count": 64015, "self": 7.238873927956547, "children": { "TorchPolicy.evaluate": { "total": 150.8589391190328, "count": 62570, "self": 150.8589391190328 } } }, "workers": { "total": 1.3996022559781522, "count": 64015, "self": 0.0, "children": { "worker_root": { "total": 3418.0171755469846, "count": 64015, "is_parallel": true, "self": 1428.4135461949995, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006838068000035946, "count": 1, "is_parallel": true, "self": 0.004324192000012772, "children": { "_process_rank_one_or_two_observation": { "total": 0.002513876000023174, "count": 8, "is_parallel": true, "self": 0.002513876000023174 } } }, "UnityEnvironment.step": { "total": 0.06349043700004131, "count": 1, "is_parallel": true, "self": 0.000732551999988118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005718710000337524, "count": 1, "is_parallel": true, "self": 0.0005718710000337524 }, "communicator.exchange": { "total": 0.060193959000002906, "count": 1, "is_parallel": true, "self": 0.060193959000002906 }, "steps_from_proto": { "total": 0.001992055000016535, "count": 1, "is_parallel": true, "self": 0.000408656999923096, "children": { "_process_rank_one_or_two_observation": { "total": 0.001583398000093439, "count": 8, "is_parallel": true, "self": 0.001583398000093439 } } } } } } }, "UnityEnvironment.step": { "total": 1989.603629351985, "count": 64014, "is_parallel": true, "self": 50.72619947687076, "children": { "UnityEnvironment._generate_step_input": { "total": 28.634496125036947, "count": 64014, "is_parallel": true, "self": 28.634496125036947 }, "communicator.exchange": { "total": 1778.3041234640268, "count": 64014, "is_parallel": true, "self": 1778.3041234640268 }, "steps_from_proto": { "total": 131.93881028605045, "count": 64014, "is_parallel": true, "self": 28.05096226509022, "children": { "_process_rank_one_or_two_observation": { "total": 103.88784802096023, "count": 512112, "is_parallel": true, "self": 103.88784802096023 } } } } } } } } } } }, "trainer_advance": { "total": 1080.459217600991, "count": 64015, "self": 4.469252293973113, "children": { "process_trajectory": { "total": 165.56075755001746, "count": 64015, "self": 165.23695537501737, "children": { "RLTrainer._checkpoint": { "total": 0.32380217500008257, "count": 2, "self": 0.32380217500008257 } } }, "_update_policy": { "total": 910.4292077570005, "count": 449, "self": 374.89932245699515, "children": { "TorchPPOOptimizer.update": { "total": 535.5298853000054, "count": 22833, "self": 535.5298853000054 } } } } } } }, "trainer_threads": { "total": 1.568999778100988e-06, "count": 1, "self": 1.568999778100988e-06 }, "TrainerController._save_models": { "total": 0.13766869700020834, "count": 1, "self": 0.002987692000260722, "children": { "RLTrainer._checkpoint": { "total": 0.13468100499994762, "count": 1, "self": 0.13468100499994762 } } } } } } }