{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6170742511749268, "min": 0.6143656373023987, "max": 1.486340045928955, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18364.12890625, "min": 18096.75390625, "max": 45089.61328125, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.29688549041748047, "min": -0.14616428315639496, "max": 0.29688549041748047, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 75.70580291748047, "min": -35.22559356689453, "max": 75.70580291748047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011791108176112175, "min": -0.007914356887340546, "max": 0.18971233069896698, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.006732702255249, "min": -1.9865036010742188, "max": 45.53096008300781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07163499392012858, "min": 0.06453474205433547, "max": 0.07383491339783065, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0745249088019286, "min": 0.5019762829566995, "max": 1.0745249088019286, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010938936094559417, "min": 5.397906408973774e-05, "max": 0.011329304711526836, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16408404141839125, "min": 0.0007557068972563283, "max": 0.16408404141839125, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.517037494353331e-06, "min": 7.517037494353331e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011275556241529997, "min": 0.00011275556241529997, "max": 0.0032551691149436996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250564666666667, "min": 0.10250564666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375847, "min": 1.3691136000000002, "max": 2.3850563000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026031410199999996, "min": 0.00026031410199999996, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039047115299999996, "min": 0.0039047115299999996, "max": 0.10852712437, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009688880294561386, "min": 0.009688880294561386, "max": 0.31505656242370605, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1453332006931305, "min": 0.13973581790924072, "max": 2.2053959369659424, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 569.3846153846154, "min": 524.7142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29608.0, "min": 15984.0, "max": 32418.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9689691996631714, "min": -1.0000000521540642, "max": 1.1159719031369477, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 50.38639838248491, "min": -32.000001668930054, "max": 63.61039847880602, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9689691996631714, "min": -1.0000000521540642, "max": 1.1159719031369477, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 50.38639838248491, "min": -32.000001668930054, "max": 63.61039847880602, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05700435822766919, "min": 0.054738789753939365, "max": 6.225681937299669, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.964226627838798, "min": 2.964226627838798, "max": 99.6109109967947, "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": "1781625763", "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": "1781628105" }, "total": 2342.3619937109997, "count": 1, "self": 0.5332995529997788, "children": { "run_training.setup": { "total": 0.03415632699989146, "count": 1, "self": 0.03415632699989146 }, "TrainerController.start_learning": { "total": 2341.794537831, "count": 1, "self": 1.5230779439370963, "children": { "TrainerController._reset_env": { "total": 2.4256196050000653, "count": 1, "self": 2.4256196050000653 }, "TrainerController.advance": { "total": 2337.754063277063, "count": 63322, "self": 1.508483210031045, "children": { "env_step": { "total": 1654.6656227980166, "count": 63322, "self": 1485.9762843809956, "children": { "SubprocessEnvManager._take_step": { "total": 167.68922224307198, "count": 63322, "self": 5.061492928973621, "children": { "TorchPolicy.evaluate": { "total": 162.62772931409836, "count": 62567, "self": 162.62772931409836 } } }, "workers": { "total": 1.0001161739489817, "count": 63322, "self": 0.0, "children": { "worker_root": { "total": 2336.1444109680037, "count": 63322, "is_parallel": true, "self": 977.7069082420012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017813899999055138, "count": 1, "is_parallel": true, "self": 0.0005981580000025133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011832319999030005, "count": 8, "is_parallel": true, "self": 0.0011832319999030005 } } }, "UnityEnvironment.step": { "total": 0.05032533499979763, "count": 1, "is_parallel": true, "self": 0.0005762659998254094, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005022870000175317, "count": 1, "is_parallel": true, "self": 0.0005022870000175317 }, "communicator.exchange": { "total": 0.04744626000001517, "count": 1, "is_parallel": true, "self": 0.04744626000001517 }, "steps_from_proto": { "total": 0.0018005219999395194, "count": 1, "is_parallel": true, "self": 0.0003842019993953727, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014163200005441468, "count": 8, "is_parallel": true, "self": 0.0014163200005441468 } } } } } } }, "UnityEnvironment.step": { "total": 1358.4375027260025, "count": 63321, "is_parallel": true, "self": 36.64394768203124, "children": { "UnityEnvironment._generate_step_input": { "total": 25.0998842529807, "count": 63321, "is_parallel": true, "self": 25.0998842529807 }, "communicator.exchange": { "total": 1179.3869115080115, "count": 63321, "is_parallel": true, "self": 1179.3869115080115 }, "steps_from_proto": { "total": 117.3067592829791, "count": 63321, "is_parallel": true, "self": 24.40840132701146, "children": { "_process_rank_one_or_two_observation": { "total": 92.89835795596764, "count": 506568, "is_parallel": true, "self": 92.89835795596764 } } } } } } } } } } }, "trainer_advance": { "total": 681.5799572690153, "count": 63322, "self": 2.8189548559798823, "children": { "process_trajectory": { "total": 126.26190328203825, "count": 63322, "self": 126.06805974503845, "children": { "RLTrainer._checkpoint": { "total": 0.1938435369997933, "count": 2, "self": 0.1938435369997933 } } }, "_update_policy": { "total": 552.4990991309971, "count": 439, "self": 304.97854429200106, "children": { "TorchPPOOptimizer.update": { "total": 247.52055483899608, "count": 22812, "self": 247.52055483899608 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.09177601000010327, "count": 1, "self": 0.0015240590000757948, "children": { "RLTrainer._checkpoint": { "total": 0.09025195100002747, "count": 1, "self": 0.09025195100002747 } } } } } } }