{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.21981509029865265, "min": 0.18506763875484467, "max": 1.411207914352417, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 6619.07177734375, "min": 5549.06787109375, "max": 42810.40234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.16111139953136444, "min": -0.1166430115699768, "max": 0.16111139953136444, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 40.27785110473633, "min": -28.110965728759766, "max": 40.27785110473633, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.16578516364097595, "min": 0.16079334914684296, "max": 0.6670405864715576, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 41.4462890625, "min": 40.359130859375, "max": 160.75677490234375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04677092236363225, "min": 0.04265627311265451, "max": 0.053192347935543456, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.7015638354544838, "min": 0.3723464355488042, "max": 0.7249526728388715, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00936165225187627, "min": 0.0005959668250766082, "max": 0.009585602481214059, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14042478377814405, "min": 0.008343535551072515, "max": 0.14042478377814405, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.527297490933331e-06, "min": 7.527297490933331e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011290946236399996, "min": 0.00011290946236399996, "max": 0.0036326935891021995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250906666666666, "min": 0.10250906666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537636, "min": 1.3886848, "max": 2.6108978, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026065575999999994, "min": 0.00026065575999999994, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003909836399999999, "min": 0.003909836399999999, "max": 0.12110869022, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.17659518122673035, "min": 0.1558270901441574, "max": 0.9753618836402893, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.648927688598633, "min": 2.181579351425171, "max": 6.82753324508667, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 645.4347826086956, "min": 645.4347826086956, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29690.0, "min": 15984.0, "max": 33287.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.6587086663297985, "min": -1.0000000521540642, "max": 0.6587086663297985, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 30.30059865117073, "min": -27.60760159045458, "max": 30.30059865117073, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.6587086663297985, "min": -1.0000000521540642, "max": 0.6587086663297985, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 30.30059865117073, "min": -27.60760159045458, "max": 30.30059865117073, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1744339446861134, "min": 1.1144351417188654, "max": 14.709853190928698, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 54.02396145556122, "min": 49.053154496476054, "max": 235.35765105485916, "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": "1744641195", "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": "1744643132" }, "total": 1937.667725711, "count": 1, "self": 0.7555339259999982, "children": { "run_training.setup": { "total": 0.028994232000059128, "count": 1, "self": 0.028994232000059128 }, "TrainerController.start_learning": { "total": 1936.883197553, "count": 1, "self": 1.445675336995464, "children": { "TrainerController._reset_env": { "total": 2.61513846999992, "count": 1, "self": 2.61513846999992 }, "TrainerController.advance": { "total": 1932.701053325004, "count": 63417, "self": 1.4852948799846217, "children": { "env_step": { "total": 1395.795611395002, "count": 63417, "self": 1228.1472580229915, "children": { "SubprocessEnvManager._take_step": { "total": 166.76848318400994, "count": 63417, "self": 4.972066104022133, "children": { "TorchPolicy.evaluate": { "total": 161.7964170799878, "count": 62562, "self": 161.7964170799878 } } }, "workers": { "total": 0.8798701880004955, "count": 63417, "self": 0.0, "children": { "worker_root": { "total": 1931.5961652650974, "count": 63417, "is_parallel": true, "self": 820.0762642761347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002836247999994157, "count": 1, "is_parallel": true, "self": 0.0008682260001933173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019680219998008397, "count": 8, "is_parallel": true, "self": 0.0019680219998008397 } } }, "UnityEnvironment.step": { "total": 0.04660052200006248, "count": 1, "is_parallel": true, "self": 0.0006330189999061986, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044072900004721305, "count": 1, "is_parallel": true, "self": 0.00044072900004721305 }, "communicator.exchange": { "total": 0.04390232800005833, "count": 1, "is_parallel": true, "self": 0.04390232800005833 }, "steps_from_proto": { "total": 0.0016244460000507388, "count": 1, "is_parallel": true, "self": 0.0003671000001759239, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012573459998748149, "count": 8, "is_parallel": true, "self": 0.0012573459998748149 } } } } } } }, "UnityEnvironment.step": { "total": 1111.5199009889627, "count": 63416, "is_parallel": true, "self": 32.12871161892508, "children": { "UnityEnvironment._generate_step_input": { "total": 23.588566452026043, "count": 63416, "is_parallel": true, "self": 23.588566452026043 }, "communicator.exchange": { "total": 956.2558198550253, "count": 63416, "is_parallel": true, "self": 956.2558198550253 }, "steps_from_proto": { "total": 99.54680306298633, "count": 63416, "is_parallel": true, "self": 20.36828647789821, "children": { "_process_rank_one_or_two_observation": { "total": 79.17851658508812, "count": 507328, "is_parallel": true, "self": 79.17851658508812 } } } } } } } } } } }, "trainer_advance": { "total": 535.4201470500175, "count": 63417, "self": 2.839436560981767, "children": { "process_trajectory": { "total": 131.3611685350345, "count": 63417, "self": 131.07835224903442, "children": { "RLTrainer._checkpoint": { "total": 0.28281628600007025, "count": 2, "self": 0.28281628600007025 } } }, "_update_policy": { "total": 401.2195419540012, "count": 455, "self": 257.8619154770297, "children": { "TorchPPOOptimizer.update": { "total": 143.35762647697152, "count": 11298, "self": 143.35762647697152 } } } } } } }, "trainer_threads": { "total": 8.700003490957897e-07, "count": 1, "self": 8.700003490957897e-07 }, "TrainerController._save_models": { "total": 0.12132955100014442, "count": 1, "self": 0.0021194979999563657, "children": { "RLTrainer._checkpoint": { "total": 0.11921005300018805, "count": 1, "self": 0.11921005300018805 } } } } } } }