{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38108545541763306, "min": 0.38108545541763306, "max": 1.4502646923065186, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11456.953125, "min": 11456.953125, "max": 43995.23046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989885.0, "min": 29952.0, "max": 989885.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.580700159072876, "min": -0.09279569983482361, "max": 0.6002334356307983, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.4346466064453, "min": -22.270967483520508, "max": 167.4651336669922, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00018589460523799062, "min": -0.00018589460523799062, "max": 0.47792017459869385, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.05167870223522186, "min": -0.05167870223522186, "max": 113.26708221435547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06829555472617763, "min": 0.0642029486905772, "max": 0.07347868600932304, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0244333208926644, "min": 0.5019391628300729, "max": 1.0483960632506448, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01591133770675191, "min": 0.0006323193366627158, "max": 0.016170097332395102, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23867006560127868, "min": 0.008852470713278021, "max": 0.23867006560127868, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.439137520319998e-06, "min": 7.439137520319998e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011158706280479998, "min": 0.00011158706280479998, "max": 0.0036347128884290994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247968, "min": 0.10247968, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371952, "min": 1.3886848, "max": 2.6115709000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025772003199999995, "min": 0.00025772003199999995, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003865800479999999, "min": 0.003865800479999999, "max": 0.12117593291, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013026198372244835, "min": 0.013026198372244835, "max": 0.5194559693336487, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19539298117160797, "min": 0.19026552140712738, "max": 3.6361918449401855, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 311.88775510204084, "min": 301.6, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30565.0, "min": 15984.0, "max": 33224.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6064550874336643, "min": -1.0000000521540642, "max": 1.6983999757303132, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 157.4325985684991, "min": -29.75680171698332, "max": 158.77399790287018, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6064550874336643, "min": -1.0000000521540642, "max": 1.6983999757303132, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 157.4325985684991, "min": -29.75680171698332, "max": 158.77399790287018, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04174828156472507, "min": 0.04174828156472507, "max": 11.16864543221891, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.091331593343057, "min": 4.064758014224935, "max": 178.69832691550255, "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": "1738859358", "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": "1738861606" }, "total": 2247.350028364, "count": 1, "self": 0.4896409330003735, "children": { "run_training.setup": { "total": 0.022402275999979793, "count": 1, "self": 0.022402275999979793 }, "TrainerController.start_learning": { "total": 2246.837985155, "count": 1, "self": 1.3803306059949136, "children": { "TrainerController._reset_env": { "total": 3.361281510000026, "count": 1, "self": 3.361281510000026 }, "TrainerController.advance": { "total": 2242.008870151005, "count": 64043, "self": 1.3749469710523954, "children": { "env_step": { "total": 1555.3213305939996, "count": 64043, "self": 1402.0470170680085, "children": { "SubprocessEnvManager._take_step": { "total": 152.48256537701627, "count": 64043, "self": 4.5754033099874505, "children": { "TorchPolicy.evaluate": { "total": 147.90716206702882, "count": 62560, "self": 147.90716206702882 } } }, "workers": { "total": 0.7917481489748752, "count": 64043, "self": 0.0, "children": { "worker_root": { "total": 2241.7443339250644, "count": 64043, "is_parallel": true, "self": 952.6183083360897, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006015026999989459, "count": 1, "is_parallel": true, "self": 0.004565960999798335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014490660001911237, "count": 8, "is_parallel": true, "self": 0.0014490660001911237 } } }, "UnityEnvironment.step": { "total": 0.11013070299998162, "count": 1, "is_parallel": true, "self": 0.0005583490000162783, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004463889999897219, "count": 1, "is_parallel": true, "self": 0.0004463889999897219 }, "communicator.exchange": { "total": 0.10224656599996251, "count": 1, "is_parallel": true, "self": 0.10224656599996251 }, "steps_from_proto": { "total": 0.006879399000013109, "count": 1, "is_parallel": true, "self": 0.005585525999890706, "children": { "_process_rank_one_or_two_observation": { "total": 0.001293873000122403, "count": 8, "is_parallel": true, "self": 0.001293873000122403 } } } } } } }, "UnityEnvironment.step": { "total": 1289.1260255889747, "count": 64042, "is_parallel": true, "self": 32.030437510974934, "children": { "UnityEnvironment._generate_step_input": { "total": 22.859823214023436, "count": 64042, "is_parallel": true, "self": 22.859823214023436 }, "communicator.exchange": { "total": 1140.9690591179813, "count": 64042, "is_parallel": true, "self": 1140.9690591179813 }, "steps_from_proto": { "total": 93.26670574599507, "count": 64042, "is_parallel": true, "self": 18.532343053978934, "children": { "_process_rank_one_or_two_observation": { "total": 74.73436269201613, "count": 512336, "is_parallel": true, "self": 74.73436269201613 } } } } } } } } } } }, "trainer_advance": { "total": 685.312592585953, "count": 64043, "self": 2.7147078639774236, "children": { "process_trajectory": { "total": 127.77151527897615, "count": 64043, "self": 127.52097887297612, "children": { "RLTrainer._checkpoint": { "total": 0.25053640600003746, "count": 2, "self": 0.25053640600003746 } } }, "_update_policy": { "total": 554.8263694429994, "count": 455, "self": 305.1522465550005, "children": { "TorchPPOOptimizer.update": { "total": 249.67412288799892, "count": 22803, "self": 249.67412288799892 } } } } } } }, "trainer_threads": { "total": 9.66999778029276e-07, "count": 1, "self": 9.66999778029276e-07 }, "TrainerController._save_models": { "total": 0.08750192100023924, "count": 1, "self": 0.0014732660001754994, "children": { "RLTrainer._checkpoint": { "total": 0.08602865500006374, "count": 1, "self": 0.08602865500006374 } } } } } } }