{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.545984148979187, "min": 0.545984148979187, "max": 1.4012805223464966, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 16353.3173828125, "min": 16353.3173828125, "max": 42509.24609375, "count": 10 }, "Pyramids.Step.mean": { "value": 299978.0, "min": 29952.0, "max": 299978.0, "count": 10 }, "Pyramids.Step.sum": { "value": 299978.0, "min": 29952.0, "max": 299978.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0906994566321373, "min": -0.12063595652580261, "max": -0.012319239787757397, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -21.76786994934082, "min": -29.19390106201172, "max": -2.9689366817474365, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04048064723610878, "min": 0.04048064723610878, "max": 0.4367198944091797, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.715354919433594, "min": 9.715354919433594, "max": 105.24949645996094, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06793504646141817, "min": 0.0664388927021007, "max": 0.07294270951093071, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8152205575370179, "min": 0.5105989665765149, "max": 0.8899881398604705, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 5.3472518289933255e-05, "min": 5.3472518289933255e-05, "max": 0.018292872316397275, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.000641670219479199, "min": 0.000641670219479199, "max": 0.1280501062147809, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5530094823333334e-05, "min": 1.5530094823333334e-05, "max": 0.0002838354339596191, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00018636113788000002, "min": 0.00018636113788000002, "max": 0.0025384261538580004, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10517666666666665, "min": 0.10517666666666665, "max": 0.19461180952380958, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.26212, "min": 1.26212, "max": 1.8879050000000002, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005271490000000002, "min": 0.0005271490000000002, "max": 0.00946171977142857, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.006325788000000002, "min": 0.006325788000000002, "max": 0.0846295858, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.03400035575032234, "min": 0.03400035575032234, "max": 0.744253933429718, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.4080042541027069, "min": 0.4080042541027069, "max": 5.209777355194092, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 938.7647058823529, "max": 999.0, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30969.0, "min": 15984.0, "max": 32731.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9998667185505231, "min": -1.0000000521540642, "max": -0.7043059317066389, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -29.996001556515694, "min": -31.99480164051056, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9998667185505231, "min": -1.0000000521540642, "max": -0.7043059317066389, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -29.996001556515694, "min": -31.99480164051056, "max": -16.000000834465027, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.3643733143496017, "min": 0.3643733143496017, "max": 16.08620097208768, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 10.93119943048805, "min": 7.6547397300601006, "max": 257.3792155534029, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713361194", "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": "1713362165" }, "total": 970.7801094100003, "count": 1, "self": 1.048138131000087, "children": { "run_training.setup": { "total": 0.10081446699996377, "count": 1, "self": 0.10081446699996377 }, "TrainerController.start_learning": { "total": 969.6311568120002, "count": 1, "self": 0.6905448039908606, "children": { "TrainerController._reset_env": { "total": 3.1021360239999467, "count": 1, "self": 3.1021360239999467 }, "TrainerController.advance": { "total": 965.6805859200092, "count": 18833, "self": 0.7974477020291033, "children": { "env_step": { "total": 611.9075689079864, "count": 18833, "self": 560.5334866859885, "children": { "SubprocessEnvManager._take_step": { "total": 50.94502648799653, "count": 18833, "self": 2.2579632349572876, "children": { "TorchPolicy.evaluate": { "total": 48.68706325303924, "count": 18785, "self": 48.68706325303924 } } }, "workers": { "total": 0.42905573400139474, "count": 18833, "self": 0.0, "children": { "worker_root": { "total": 967.3851138180214, "count": 18833, "is_parallel": true, "self": 465.1966439570276, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003243763999989824, "count": 1, "is_parallel": true, "self": 0.001038993000292976, "children": { "_process_rank_one_or_two_observation": { "total": 0.002204770999696848, "count": 8, "is_parallel": true, "self": 0.002204770999696848 } } }, "UnityEnvironment.step": { "total": 0.06428034400005345, "count": 1, "is_parallel": true, "self": 0.0007885420002367027, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005795919998945465, "count": 1, "is_parallel": true, "self": 0.0005795919998945465 }, "communicator.exchange": { "total": 0.06085026300002028, "count": 1, "is_parallel": true, "self": 0.06085026300002028 }, "steps_from_proto": { "total": 0.00206194699990192, "count": 1, "is_parallel": true, "self": 0.00041605899991736806, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016458879999845522, "count": 8, "is_parallel": true, "self": 0.0016458879999845522 } } } } } } }, "UnityEnvironment.step": { "total": 502.1884698609938, "count": 18832, "is_parallel": true, "self": 15.713278678990719, "children": { "UnityEnvironment._generate_step_input": { "total": 9.906426000998863, "count": 18832, "is_parallel": true, "self": 9.906426000998863 }, "communicator.exchange": { "total": 435.82871424098926, "count": 18832, "is_parallel": true, "self": 435.82871424098926 }, "steps_from_proto": { "total": 40.74005094001495, "count": 18832, "is_parallel": true, "self": 8.795431370017468, "children": { "_process_rank_one_or_two_observation": { "total": 31.944619569997485, "count": 150656, "is_parallel": true, "self": 31.944619569997485 } } } } } } } } } } }, "trainer_advance": { "total": 352.9755693099937, "count": 18833, "self": 1.0590634869779478, "children": { "process_trajectory": { "total": 50.7296700280167, "count": 18833, "self": 50.7296700280167 }, "_update_policy": { "total": 301.18683579499907, "count": 110, "self": 118.65491317399301, "children": { "TorchPPOOptimizer.update": { "total": 182.53192262100606, "count": 6891, "self": 182.53192262100606 } } } } } } }, "trainer_threads": { "total": 1.6130002222780604e-06, "count": 1, "self": 1.6130002222780604e-06 }, "TrainerController._save_models": { "total": 0.15788845099996252, "count": 1, "self": 0.0030406880000555248, "children": { "RLTrainer._checkpoint": { "total": 0.154847762999907, "count": 1, "self": 0.154847762999907 } } } } } } }