{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48113754391670227, "min": 0.48113754391670227, "max": 1.4965922832489014, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14387.9375, "min": 14387.9375, "max": 45400.625, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29952.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39388731122016907, "min": -0.22138603031635284, "max": 0.415062814950943, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 105.16791534423828, "min": -52.46849060058594, "max": 110.82176971435547, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13206982612609863, "min": -0.016104351729154587, "max": 0.14079056680202484, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 35.26264190673828, "min": -3.8167314529418945, "max": 35.26264190673828, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0679019823618946, "min": 0.06373399406965334, "max": 0.07350037375865559, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9506277530665244, "min": 0.4915210843043925, "max": 1.0746568132761989, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017977983889633696, "min": 9.973710540963505e-05, "max": 0.017977983889633696, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25169177445487173, "min": 0.0012965823703252556, "max": 0.25169177445487173, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.358690404278567e-06, "min": 7.358690404278567e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010302166565989994, "min": 0.00010302166565989994, "max": 0.0030553272815575998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245286428571429, "min": 0.10245286428571429, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343401, "min": 1.3886848, "max": 2.3176053, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002550411421428571, "min": 0.0002550411421428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035705759899999994, "min": 0.0035705759899999994, "max": 0.10185239576, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011029532179236412, "min": 0.011021354235708714, "max": 0.3633356988430023, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15441344678401947, "min": 0.15429896116256714, "max": 2.5433499813079834, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 462.09090909090907, "min": 416.85915492957747, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30498.0, "min": 15984.0, "max": 32958.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3863636167211966, "min": -1.0000000521540642, "max": 1.3863636167211966, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 91.49999870359898, "min": -31.998801663517952, "max": 98.3977991938591, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3863636167211966, "min": -1.0000000521540642, "max": 1.3863636167211966, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 91.49999870359898, "min": -31.998801663517952, "max": 98.3977991938591, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05270289359561337, "min": 0.04958969265842338, "max": 7.060105485841632, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4783909773104824, "min": 3.0526737466279883, "max": 112.96168777346611, "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": "1706955174", "python_version": "3.10.12 (main, Jul 5 2023, 19:22:19) [GCC 11.2.0]", "command_line_arguments": "/home/abdelrhman/anaconda3/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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706956692" }, "total": 1517.7048791140114, "count": 1, "self": 0.5711877430148888, "children": { "run_training.setup": { "total": 0.08145934599451721, "count": 1, "self": 0.08145934599451721 }, "TrainerController.start_learning": { "total": 1517.052232025002, "count": 1, "self": 1.2149255121476017, "children": { "TrainerController._reset_env": { "total": 8.832999819001998, "count": 1, "self": 8.832999819001998 }, "TrainerController.advance": { "total": 1506.9243591348495, "count": 63438, "self": 1.2376328914397163, "children": { "env_step": { "total": 969.1310728598328, "count": 63438, "self": 886.514404017289, "children": { "SubprocessEnvManager._take_step": { "total": 81.78074071451556, "count": 63438, "self": 3.6783674093312584, "children": { "TorchPolicy.evaluate": { "total": 78.1023733051843, "count": 62577, "self": 78.1023733051843 } } }, "workers": { "total": 0.8359281280281721, "count": 63438, "self": 0.0, "children": { "worker_root": { "total": 1515.0705137423938, "count": 63438, "is_parallel": true, "self": 721.6951992948743, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013213839993113652, "count": 1, "is_parallel": true, "self": 0.0003843690064968541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009370149928145111, "count": 8, "is_parallel": true, "self": 0.0009370149928145111 } } }, "UnityEnvironment.step": { "total": 0.0529286530072568, "count": 1, "is_parallel": true, "self": 0.000914744014153257, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010949629941023886, "count": 1, "is_parallel": true, "self": 0.0010949629941023886 }, "communicator.exchange": { "total": 0.048805448997882195, "count": 1, "is_parallel": true, "self": 0.048805448997882195 }, "steps_from_proto": { "total": 0.002113497001118958, "count": 1, "is_parallel": true, "self": 0.00036421297409106046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017492840270278975, "count": 8, "is_parallel": true, "self": 0.0017492840270278975 } } } } } } }, "UnityEnvironment.step": { "total": 793.3753144475195, "count": 63437, "is_parallel": true, "self": 25.353662472465658, "children": { "UnityEnvironment._generate_step_input": { "total": 18.055158000031952, "count": 63437, "is_parallel": true, "self": 18.055158000031952 }, "communicator.exchange": { "total": 680.3304307133658, "count": 63437, "is_parallel": true, "self": 680.3304307133658 }, "steps_from_proto": { "total": 69.63606326165609, "count": 63437, "is_parallel": true, "self": 14.447206584518426, "children": { "_process_rank_one_or_two_observation": { "total": 55.188856677137665, "count": 507496, "is_parallel": true, "self": 55.188856677137665 } } } } } } } } } } }, "trainer_advance": { "total": 536.555653383577, "count": 63438, "self": 2.1428603102394845, "children": { "process_trajectory": { "total": 88.26711224931933, "count": 63438, "self": 87.24127948531532, "children": { "RLTrainer._checkpoint": { "total": 1.025832764004008, "count": 2, "self": 1.025832764004008 } } }, "_update_policy": { "total": 446.1456808240182, "count": 438, "self": 218.53548027201032, "children": { "TorchPPOOptimizer.update": { "total": 227.61020055200788, "count": 22881, "self": 227.61020055200788 } } } } } } }, "trainer_threads": { "total": 1.3870012480765581e-06, "count": 1, "self": 1.3870012480765581e-06 }, "TrainerController._save_models": { "total": 0.07994617200165521, "count": 1, "self": 0.0012979600141989067, "children": { "RLTrainer._checkpoint": { "total": 0.0786482119874563, "count": 1, "self": 0.0786482119874563 } } } } } } }