{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3857576549053192, "min": 0.3857576549053192, "max": 1.4002728462219238, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11690.0, "min": 11557.279296875, "max": 42478.67578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989944.0, "min": 29952.0, "max": 989944.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4349876046180725, "min": -0.1013028621673584, "max": 0.44215232133865356, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.83673095703125, "min": -24.413990020751953, "max": 118.93897247314453, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.003222506260499358, "min": -0.00939944852143526, "max": 0.39375215768814087, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8507416248321533, "min": -2.453256130218506, "max": 93.31925964355469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06795283165272502, "min": 0.06644769970452183, "max": 0.07401672352955015, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9513396431381503, "min": 0.49369668438943665, "max": 1.075621556910668, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013575619249119578, "min": 0.0011979246234343056, "max": 0.013807247448967485, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19005866948767408, "min": 0.013420961168740933, "max": 0.20710871173451226, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5363760593357165e-06, "min": 7.5363760593357165e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010550926483070004, "min": 0.00010550926483070004, "max": 0.0035073611308797, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251209285714287, "min": 0.10251209285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351693, "min": 1.3886848, "max": 2.5691203000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026095807642857163, "min": 0.00026095807642857163, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036534130700000026, "min": 0.0036534130700000026, "max": 0.11693511796999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007567566819489002, "min": 0.007565208710730076, "max": 0.5547627210617065, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10594593733549118, "min": 0.10591292381286621, "max": 3.8833391666412354, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.05479452054794, "min": 381.2278481012658, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28620.0, "min": 15984.0, "max": 33420.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.416101348216403, "min": -1.0000000521540642, "max": 1.441506311391728, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.37539841979742, "min": -30.76340176910162, "max": 113.8789985999465, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.416101348216403, "min": -1.0000000521540642, "max": 1.441506311391728, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.37539841979742, "min": -30.76340176910162, "max": 113.8789985999465, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030801734485590117, "min": 0.030801734485590117, "max": 11.505982162430882, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2485266174480785, "min": 2.2485266174480785, "max": 184.09571459889412, "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": "1719227379", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719229545" }, "total": 2166.3301188490004, "count": 1, "self": 0.477593810000144, "children": { "run_training.setup": { "total": 0.05040156799987017, "count": 1, "self": 0.05040156799987017 }, "TrainerController.start_learning": { "total": 2165.8021234710004, "count": 1, "self": 1.3859239009839257, "children": { "TrainerController._reset_env": { "total": 3.0494677980000233, "count": 1, "self": 3.0494677980000233 }, "TrainerController.advance": { "total": 2161.2829154310166, "count": 63614, "self": 1.3968209089589436, "children": { "env_step": { "total": 1526.207784086941, "count": 63614, "self": 1390.8850098949335, "children": { "SubprocessEnvManager._take_step": { "total": 134.51494166698103, "count": 63614, "self": 4.632543766002755, "children": { "TorchPolicy.evaluate": { "total": 129.88239790097828, "count": 62550, "self": 129.88239790097828 } } }, "workers": { "total": 0.8078325250264697, "count": 63614, "self": 0.0, "children": { "worker_root": { "total": 2160.685330722004, "count": 63614, "is_parallel": true, "self": 891.5505974640191, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020780120000836177, "count": 1, "is_parallel": true, "self": 0.0006042730003628094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014737389997208084, "count": 8, "is_parallel": true, "self": 0.0014737389997208084 } } }, "UnityEnvironment.step": { "total": 0.07416361200012034, "count": 1, "is_parallel": true, "self": 0.0006517510000776383, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004143260000546434, "count": 1, "is_parallel": true, "self": 0.0004143260000546434 }, "communicator.exchange": { "total": 0.059508003000019016, "count": 1, "is_parallel": true, "self": 0.059508003000019016 }, "steps_from_proto": { "total": 0.01358953199996904, "count": 1, "is_parallel": true, "self": 0.00036488899991127255, "children": { "_process_rank_one_or_two_observation": { "total": 0.013224643000057767, "count": 8, "is_parallel": true, "self": 0.013224643000057767 } } } } } } }, "UnityEnvironment.step": { "total": 1269.1347332579849, "count": 63613, "is_parallel": true, "self": 33.74526759299397, "children": { "UnityEnvironment._generate_step_input": { "total": 23.182139034026022, "count": 63613, "is_parallel": true, "self": 23.182139034026022 }, "communicator.exchange": { "total": 1115.742784193941, "count": 63613, "is_parallel": true, "self": 1115.742784193941 }, "steps_from_proto": { "total": 96.46454243702397, "count": 63613, "is_parallel": true, "self": 19.336567039863212, "children": { "_process_rank_one_or_two_observation": { "total": 77.12797539716075, "count": 508904, "is_parallel": true, "self": 77.12797539716075 } } } } } } } } } } }, "trainer_advance": { "total": 633.6783104351164, "count": 63614, "self": 2.6757331951214383, "children": { "process_trajectory": { "total": 126.15475835499433, "count": 63614, "self": 125.89464509099412, "children": { "RLTrainer._checkpoint": { "total": 0.2601132640002106, "count": 2, "self": 0.2601132640002106 } } }, "_update_policy": { "total": 504.8478188850006, "count": 449, "self": 297.2448795539374, "children": { "TorchPPOOptimizer.update": { "total": 207.60293933106323, "count": 22815, "self": 207.60293933106323 } } } } } } }, "trainer_threads": { "total": 9.88000010693213e-07, "count": 1, "self": 9.88000010693213e-07 }, "TrainerController._save_models": { "total": 0.08381535299986353, "count": 1, "self": 0.0012948500002494256, "children": { "RLTrainer._checkpoint": { "total": 0.08252050299961411, "count": 1, "self": 0.08252050299961411 } } } } } } }