{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4711191952228546, "min": 0.4710032045841217, "max": 1.4566848278045654, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14322.0234375, "min": 14009.51953125, "max": 44189.9921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989933.0, "min": 29913.0, "max": 989933.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989933.0, "min": 29913.0, "max": 989933.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5604043006896973, "min": -0.10009252279996872, "max": 0.5604043006896973, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 154.6715850830078, "min": -24.022205352783203, "max": 154.6715850830078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004798299167305231, "min": -0.004798299167305231, "max": 0.41382119059562683, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.3243305683135986, "min": -1.3243305683135986, "max": 98.07562255859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07046820363999966, "min": 0.06454239811999196, "max": 0.07275140910203785, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0570230545999948, "min": 0.5022655993920145, "max": 1.0570230545999948, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013498891087430014, "min": 0.0002709059132803266, "max": 0.015891602118028373, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2024833663114502, "min": 0.0035217768726442454, "max": 0.2224824296523972, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.499057500346667e-06, "min": 7.499057500346667e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011248586250520001, "min": 0.00011248586250520001, "max": 0.0034928182357272996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249965333333334, "min": 0.10249965333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374948000000002, "min": 1.3886848, "max": 2.4850600000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002597153680000001, "min": 0.0002597153680000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038957305200000014, "min": 0.0038957305200000014, "max": 0.11644084273, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009860632009804249, "min": 0.009731153957545757, "max": 0.49076297879219055, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.147909477353096, "min": 0.13623616099357605, "max": 3.4353408813476562, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 355.32530120481925, "min": 338.6136363636364, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29492.0, "min": 16840.0, "max": 32953.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5723638320902744, "min": -0.9999625529162586, "max": 1.6129829082183722, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.50619806349277, "min": -31.998801693320274, "max": 140.1997983008623, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5723638320902744, "min": -0.9999625529162586, "max": 1.6129829082183722, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.50619806349277, "min": -31.998801693320274, "max": 140.1997983008623, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03685701524972753, "min": 0.03481395565524343, "max": 9.516234925564598, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.059132265727385, "min": 3.059132265727385, "max": 161.77599373459816, "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": "1715682540", "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": "1715684893" }, "total": 2353.1123616269997, "count": 1, "self": 0.5411571389995515, "children": { "run_training.setup": { "total": 0.05753919999995105, "count": 1, "self": 0.05753919999995105 }, "TrainerController.start_learning": { "total": 2352.513665288, "count": 1, "self": 1.4265083560430867, "children": { "TrainerController._reset_env": { "total": 3.210276040999929, "count": 1, "self": 3.210276040999929 }, "TrainerController.advance": { "total": 2347.7754697839573, "count": 63731, "self": 1.613702117883804, "children": { "env_step": { "total": 1659.124722343016, "count": 63731, "self": 1514.8443046880175, "children": { "SubprocessEnvManager._take_step": { "total": 143.32296246401256, "count": 63731, "self": 4.929438565012902, "children": { "TorchPolicy.evaluate": { "total": 138.39352389899966, "count": 62556, "self": 138.39352389899966 } } }, "workers": { "total": 0.9574551909857973, "count": 63731, "self": 0.0, "children": { "worker_root": { "total": 2346.9911806209984, "count": 63731, "is_parallel": true, "self": 962.9359716419897, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006449769000028027, "count": 1, "is_parallel": true, "self": 0.004841146000103436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016086229999245916, "count": 8, "is_parallel": true, "self": 0.0016086229999245916 } } }, "UnityEnvironment.step": { "total": 0.05573274899995795, "count": 1, "is_parallel": true, "self": 0.0007654180000145061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000580947000003107, "count": 1, "is_parallel": true, "self": 0.000580947000003107 }, "communicator.exchange": { "total": 0.05241336400001728, "count": 1, "is_parallel": true, "self": 0.05241336400001728 }, "steps_from_proto": { "total": 0.0019730199999230535, "count": 1, "is_parallel": true, "self": 0.0004123209998851962, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015606990000378573, "count": 8, "is_parallel": true, "self": 0.0015606990000378573 } } } } } } }, "UnityEnvironment.step": { "total": 1384.0552089790087, "count": 63730, "is_parallel": true, "self": 35.09301207501812, "children": { "UnityEnvironment._generate_step_input": { "total": 24.045127350976486, "count": 63730, "is_parallel": true, "self": 24.045127350976486 }, "communicator.exchange": { "total": 1223.7188198789927, "count": 63730, "is_parallel": true, "self": 1223.7188198789927 }, "steps_from_proto": { "total": 101.19824967402133, "count": 63730, "is_parallel": true, "self": 20.963837166098415, "children": { "_process_rank_one_or_two_observation": { "total": 80.23441250792291, "count": 509840, "is_parallel": true, "self": 80.23441250792291 } } } } } } } } } } }, "trainer_advance": { "total": 687.0370453230573, "count": 63731, "self": 3.196197453058744, "children": { "process_trajectory": { "total": 140.83748497699594, "count": 63731, "self": 140.53517245099601, "children": { "RLTrainer._checkpoint": { "total": 0.3023125259999233, "count": 2, "self": 0.3023125259999233 } } }, "_update_policy": { "total": 543.0033628930026, "count": 453, "self": 320.4261366090161, "children": { "TorchPPOOptimizer.update": { "total": 222.57722628398653, "count": 22776, "self": 222.57722628398653 } } } } } } }, "trainer_threads": { "total": 1.485000211687293e-06, "count": 1, "self": 1.485000211687293e-06 }, "TrainerController._save_models": { "total": 0.10140962199966452, "count": 1, "self": 0.0015343309996751486, "children": { "RLTrainer._checkpoint": { "total": 0.09987529099998937, "count": 1, "self": 0.09987529099998937 } } } } } } }