{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32878488302230835, "min": 0.32246193289756775, "max": 1.4604836702346802, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9826.72265625, "min": 9596.466796875, "max": 44305.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989880.0, "min": 29952.0, "max": 989880.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5758415460586548, "min": -0.09487657248973846, "max": 0.5931008458137512, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 161.23562622070312, "min": -22.77037811279297, "max": 166.0682373046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01898706704378128, "min": -0.002882631728425622, "max": 0.6427660584449768, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.316378593444824, "min": -0.7523669004440308, "max": 152.33555603027344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06714911195801711, "min": 0.06549509007128931, "max": 0.07324526347691149, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9400875674122395, "min": 0.4843161457909697, "max": 1.0635648523765509, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016600934738631286, "min": 0.000512829270221263, "max": 0.016600934738631286, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23241308634083802, "min": 0.00666678051287642, "max": 0.23241308634083802, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.27053329080714e-06, "min": 7.27053329080714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010178746607129995, "min": 0.00010178746607129995, "max": 0.0033717361760879994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024234785714286, "min": 0.1024234785714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339287000000003, "min": 1.3691136000000002, "max": 2.4827047, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002521055092857142, "min": 0.0002521055092857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003529477129999999, "min": 0.003529477129999999, "max": 0.11240880880000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0170926284044981, "min": 0.0170926284044981, "max": 0.6427498459815979, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2392968088388443, "min": 0.2392968088388443, "max": 4.49924898147583, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.1011235955056, "min": 313.1011235955056, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27866.0, "min": 15984.0, "max": 32936.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.641946050055911, "min": -1.0000000521540642, "max": 1.641946050055911, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 146.13319845497608, "min": -32.000001668930054, "max": 150.07859824597836, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.641946050055911, "min": -1.0000000521540642, "max": 1.641946050055911, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 146.13319845497608, "min": -32.000001668930054, "max": 150.07859824597836, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0555063476824441, "min": 0.0555063476824441, "max": 13.248439649119973, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.940064943737525, "min": 4.940064943737525, "max": 211.97503438591957, "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": "1684205590", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684207789" }, "total": 2198.888636739, "count": 1, "self": 0.8611600179997367, "children": { "run_training.setup": { "total": 0.03643745400017906, "count": 1, "self": 0.03643745400017906 }, "TrainerController.start_learning": { "total": 2197.991039267, "count": 1, "self": 1.3938664479983345, "children": { "TrainerController._reset_env": { "total": 4.267176667000058, "count": 1, "self": 4.267176667000058 }, "TrainerController.advance": { "total": 2192.181663918001, "count": 63916, "self": 1.4234841100801532, "children": { "env_step": { "total": 1554.1403072788873, "count": 63916, "self": 1442.7388023159372, "children": { "SubprocessEnvManager._take_step": { "total": 110.5719351539733, "count": 63916, "self": 4.854189530951999, "children": { "TorchPolicy.evaluate": { "total": 105.7177456230213, "count": 62553, "self": 105.7177456230213 } } }, "workers": { "total": 0.8295698089768848, "count": 63916, "self": 0.0, "children": { "worker_root": { "total": 2193.025245738993, "count": 63916, "is_parallel": true, "self": 865.8742121289631, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020236880000084057, "count": 1, "is_parallel": true, "self": 0.0005709960003059678, "children": { "_process_rank_one_or_two_observation": { "total": 0.001452691999702438, "count": 8, "is_parallel": true, "self": 0.001452691999702438 } } }, "UnityEnvironment.step": { "total": 0.08537902100010797, "count": 1, "is_parallel": true, "self": 0.0005109280000397121, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048063099984574364, "count": 1, "is_parallel": true, "self": 0.00048063099984574364 }, "communicator.exchange": { "total": 0.08260350600016864, "count": 1, "is_parallel": true, "self": 0.08260350600016864 }, "steps_from_proto": { "total": 0.0017839560000538768, "count": 1, "is_parallel": true, "self": 0.00038560200050596904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013983539995479077, "count": 8, "is_parallel": true, "self": 0.0013983539995479077 } } } } } } }, "UnityEnvironment.step": { "total": 1327.1510336100298, "count": 63915, "is_parallel": true, "self": 31.54319480709205, "children": { "UnityEnvironment._generate_step_input": { "total": 23.79417101392687, "count": 63915, "is_parallel": true, "self": 23.79417101392687 }, "communicator.exchange": { "total": 1169.8276906140693, "count": 63915, "is_parallel": true, "self": 1169.8276906140693 }, "steps_from_proto": { "total": 101.98597717494158, "count": 63915, "is_parallel": true, "self": 21.11755114705329, "children": { "_process_rank_one_or_two_observation": { "total": 80.86842602788829, "count": 511320, "is_parallel": true, "self": 80.86842602788829 } } } } } } } } } } }, "trainer_advance": { "total": 636.6178725290335, "count": 63916, "self": 2.6338825119707963, "children": { "process_trajectory": { "total": 111.53061204206801, "count": 63916, "self": 111.20962144906775, "children": { "RLTrainer._checkpoint": { "total": 0.32099059300026056, "count": 2, "self": 0.32099059300026056 } } }, "_update_policy": { "total": 522.4533779749947, "count": 448, "self": 339.5383629850419, "children": { "TorchPPOOptimizer.update": { "total": 182.91501498995285, "count": 22794, "self": 182.91501498995285 } } } } } } }, "trainer_threads": { "total": 1.1710003491316456e-06, "count": 1, "self": 1.1710003491316456e-06 }, "TrainerController._save_models": { "total": 0.14833106300011423, "count": 1, "self": 0.0020780289996764623, "children": { "RLTrainer._checkpoint": { "total": 0.14625303400043776, "count": 1, "self": 0.14625303400043776 } } } } } } }