{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3333851993083954, "min": 0.3333851993083954, "max": 1.3748527765274048, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9942.8798828125, "min": 9942.8798828125, "max": 41707.53515625, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4651373028755188, "min": -0.10162311047315598, "max": 0.4809064269065857, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.65679931640625, "min": -24.491168975830078, "max": 129.28665161132812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004104089457541704, "min": 0.004104089457541704, "max": 0.445652574300766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.09989595413208, "min": 1.09989595413208, "max": 105.61965942382812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06635038664847213, "min": 0.06439323306403821, "max": 0.07328349461523014, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.92890541307861, "min": 0.4955841273143981, "max": 1.0416657784953713, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015057953767349575, "min": 0.00021358863267207685, "max": 0.015057953767349575, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21081135274289406, "min": 0.0025630635920649222, "max": 0.21081135274289406, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.578590330978572e-06, "min": 7.578590330978572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010610026463370001, "min": 0.00010610026463370001, "max": 0.0031379888540038, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025261642857143, "min": 0.1025261642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353663000000003, "min": 1.3886848, "max": 2.5275828000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002623638121428572, "min": 0.0002623638121428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003673093370000001, "min": 0.003673093370000001, "max": 0.10462502038, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010203810408711433, "min": 0.010145933367311954, "max": 0.46275368332862854, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14285334944725037, "min": 0.14277057349681854, "max": 3.2392756938934326, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 382.4320987654321, "min": 376.1081081081081, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30977.0, "min": 15984.0, "max": 33068.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5187777612864235, "min": -1.0000000521540642, "max": 1.5187777612864235, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.0209986642003, "min": -31.997201666235924, "max": 123.0209986642003, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5187777612864235, "min": -1.0000000521540642, "max": 1.5187777612864235, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.0209986642003, "min": -31.997201666235924, "max": 123.0209986642003, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04046169868857243, "min": 0.04046169868857243, "max": 9.877677977085114, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.277397593774367, "min": 3.1699138503317954, "max": 158.04284763336182, "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": "1740414831", "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": "1740416938" }, "total": 2106.945349081, "count": 1, "self": 0.8567794010004945, "children": { "run_training.setup": { "total": 0.020360995999908482, "count": 1, "self": 0.020360995999908482 }, "TrainerController.start_learning": { "total": 2106.0682086839997, "count": 1, "self": 1.3336890339551246, "children": { "TrainerController._reset_env": { "total": 2.224771382999961, "count": 1, "self": 2.224771382999961 }, "TrainerController.advance": { "total": 2102.382607587044, "count": 63687, "self": 1.3385691040002712, "children": { "env_step": { "total": 1428.679225282015, "count": 63687, "self": 1276.6734434491073, "children": { "SubprocessEnvManager._take_step": { "total": 151.22640124094733, "count": 63687, "self": 4.541878820966986, "children": { "TorchPolicy.evaluate": { "total": 146.68452241998034, "count": 62547, "self": 146.68452241998034 } } }, "workers": { "total": 0.7793805919604893, "count": 63687, "self": 0.0, "children": { "worker_root": { "total": 2101.231791547012, "count": 63687, "is_parallel": true, "self": 931.7105563019941, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020379969998884917, "count": 1, "is_parallel": true, "self": 0.0006690420000268205, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013689549998616712, "count": 8, "is_parallel": true, "self": 0.0013689549998616712 } } }, "UnityEnvironment.step": { "total": 0.05033628900014264, "count": 1, "is_parallel": true, "self": 0.0005550970001877431, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004715679999662825, "count": 1, "is_parallel": true, "self": 0.0004715679999662825 }, "communicator.exchange": { "total": 0.0475681519999398, "count": 1, "is_parallel": true, "self": 0.0475681519999398 }, "steps_from_proto": { "total": 0.001741472000048816, "count": 1, "is_parallel": true, "self": 0.0003493070007607457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013921649992880702, "count": 8, "is_parallel": true, "self": 0.0013921649992880702 } } } } } } }, "UnityEnvironment.step": { "total": 1169.521235245018, "count": 63686, "is_parallel": true, "self": 30.788529234074076, "children": { "UnityEnvironment._generate_step_input": { "total": 22.549632131961744, "count": 63686, "is_parallel": true, "self": 22.549632131961744 }, "communicator.exchange": { "total": 1024.3307892419703, "count": 63686, "is_parallel": true, "self": 1024.3307892419703 }, "steps_from_proto": { "total": 91.85228463701196, "count": 63686, "is_parallel": true, "self": 17.953285928951118, "children": { "_process_rank_one_or_two_observation": { "total": 73.89899870806084, "count": 509488, "is_parallel": true, "self": 73.89899870806084 } } } } } } } } } } }, "trainer_advance": { "total": 672.3648132010283, "count": 63687, "self": 2.5906320790063546, "children": { "process_trajectory": { "total": 124.83240148602727, "count": 63687, "self": 124.5946904720272, "children": { "RLTrainer._checkpoint": { "total": 0.23771101400006955, "count": 2, "self": 0.23771101400006955 } } }, "_update_policy": { "total": 544.9417796359946, "count": 445, "self": 299.1745034909636, "children": { "TorchPPOOptimizer.update": { "total": 245.76727614503102, "count": 22827, "self": 245.76727614503102 } } } } } } }, "trainer_threads": { "total": 1.2130003597121686e-06, "count": 1, "self": 1.2130003597121686e-06 }, "TrainerController._save_models": { "total": 0.1271394670002337, "count": 1, "self": 0.001882250000107888, "children": { "RLTrainer._checkpoint": { "total": 0.12525721700012582, "count": 1, "self": 0.12525721700012582 } } } } } } }