{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4563881456851959, "min": 0.4563881456851959, "max": 1.44721519947052, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13757.3642578125, "min": 13757.3642578125, "max": 43902.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29903.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29903.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.28028613328933716, "min": -0.10673309117555618, "max": 0.3540996015071869, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 72.03353881835938, "min": -25.722675323486328, "max": 94.19049072265625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -3.7643654346466064, "min": -3.7643654346466064, "max": 0.3398297131061554, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -967.44189453125, "min": -967.44189453125, "max": 81.55912780761719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06917446291620201, "min": 0.06577435550845342, "max": 0.07360288635268364, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9684424808268282, "min": 0.5888230908214691, "max": 1.030876987960701, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 2.21124804902467, "min": 0.00021858882359409603, "max": 2.21124804902467, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 30.95747268634538, "min": 0.0028416547067232484, "max": 30.95747268634538, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.63344745555e-06, "min": 7.63344745555e-06, "max": 0.0002950140391619875, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010686826437770001, "min": 0.00010686826437770001, "max": 0.0033757867747378, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254445000000001, "min": 0.10254445000000001, "max": 0.1983380125, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356223000000001, "min": 1.4356223000000001, "max": 2.4252622, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002641905550000001, "min": 0.0002641905550000001, "max": 0.00983396744875, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036986677700000014, "min": 0.0036986677700000014, "max": 0.11254369378000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.019229937344789505, "min": 0.019229937344789505, "max": 0.5228409767150879, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.26921913027763367, "min": 0.26921913027763367, "max": 4.182727813720703, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 615.1346153846154, "min": 457.4852941176471, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31987.0, "min": 17725.0, "max": 33651.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9616615065874962, "min": -0.9999867188433806, "max": 1.3071470317595146, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 50.0063983425498, "min": -31.99480165541172, "max": 88.88599815964699, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9616615065874962, "min": -0.9999867188433806, "max": 1.3071470317595146, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 50.0063983425498, "min": -31.99480165541172, "max": 88.88599815964699, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12207683166679299, "min": 0.09240759628643419, "max": 10.130403281913864, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 6.347995246673236, "min": 5.7659988483646885, "max": 182.34725907444954, "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": "1725291168", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725293616" }, "total": 2448.0873914760004, "count": 1, "self": 0.8617520630004947, "children": { "run_training.setup": { "total": 0.05131528299989441, "count": 1, "self": 0.05131528299989441 }, "TrainerController.start_learning": { "total": 2447.17432413, "count": 1, "self": 1.7349560708867102, "children": { "TrainerController._reset_env": { "total": 1.8402889809999579, "count": 1, "self": 1.8402889809999579 }, "TrainerController.advance": { "total": 2443.4658142671133, "count": 63401, "self": 1.7134043972237123, "children": { "env_step": { "total": 1724.426871784899, "count": 63401, "self": 1543.309353418973, "children": { "SubprocessEnvManager._take_step": { "total": 180.0822541440166, "count": 63401, "self": 5.460628124933919, "children": { "TorchPolicy.evaluate": { "total": 174.62162601908267, "count": 62549, "self": 174.62162601908267 } } }, "workers": { "total": 1.0352642219095287, "count": 63401, "self": 0.0, "children": { "worker_root": { "total": 2440.933938096043, "count": 63401, "is_parallel": true, "self": 1039.5990222800424, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020940360000167857, "count": 1, "is_parallel": true, "self": 0.0006395569998858264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014544790001309593, "count": 8, "is_parallel": true, "self": 0.0014544790001309593 } } }, "UnityEnvironment.step": { "total": 0.053829552000024705, "count": 1, "is_parallel": true, "self": 0.0006610780005757988, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005251039997347107, "count": 1, "is_parallel": true, "self": 0.0005251039997347107 }, "communicator.exchange": { "total": 0.050836751999668195, "count": 1, "is_parallel": true, "self": 0.050836751999668195 }, "steps_from_proto": { "total": 0.0018066180000460008, "count": 1, "is_parallel": true, "self": 0.0003727560010702291, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014338619989757717, "count": 8, "is_parallel": true, "self": 0.0014338619989757717 } } } } } } }, "UnityEnvironment.step": { "total": 1401.3349158160008, "count": 63400, "is_parallel": true, "self": 37.504137657034335, "children": { "UnityEnvironment._generate_step_input": { "total": 25.411732322994794, "count": 63400, "is_parallel": true, "self": 25.411732322994794 }, "communicator.exchange": { "total": 1227.4459511028986, "count": 63400, "is_parallel": true, "self": 1227.4459511028986 }, "steps_from_proto": { "total": 110.97309473307314, "count": 63400, "is_parallel": true, "self": 23.928493201397032, "children": { "_process_rank_one_or_two_observation": { "total": 87.04460153167611, "count": 507200, "is_parallel": true, "self": 87.04460153167611 } } } } } } } } } } }, "trainer_advance": { "total": 717.3255380849905, "count": 63401, "self": 3.183504046019607, "children": { "process_trajectory": { "total": 141.20301701297603, "count": 63401, "self": 140.94942152797603, "children": { "RLTrainer._checkpoint": { "total": 0.2535954850000053, "count": 2, "self": 0.2535954850000053 } } }, "_update_policy": { "total": 572.9390170259949, "count": 451, "self": 323.7157642169914, "children": { "TorchPPOOptimizer.update": { "total": 249.2232528090035, "count": 22827, "self": 249.2232528090035 } } } } } } }, "trainer_threads": { "total": 1.4620000001741573e-06, "count": 1, "self": 1.4620000001741573e-06 }, "TrainerController._save_models": { "total": 0.13326334900011716, "count": 1, "self": 0.002368839000155276, "children": { "RLTrainer._checkpoint": { "total": 0.13089450999996188, "count": 1, "self": 0.13089450999996188 } } } } } } }