{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2594893276691437, "min": 0.2527059316635132, "max": 0.29336464405059814, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 7834.501953125, "min": 7621.611328125, "max": 8843.18359375, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.9191919191919, "min": 275.46153846153845, "max": 329.9318181818182, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29890.0, "min": 27206.0, "max": 31775.0, "count": 10 }, "Pyramids.Step.mean": { "value": 1499906.0, "min": 1229910.0, "max": 1499906.0, "count": 10 }, "Pyramids.Step.sum": { "value": 1499906.0, "min": 1229910.0, "max": 1499906.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.616241455078125, "min": 0.578735888004303, "max": 0.6740180850028992, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.86129760742188, "min": 162.04605102539062, "max": 197.4873046875, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.01872764341533184, "min": -0.01872764341533184, "max": 0.02947433665394783, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -5.374833583831787, "min": -5.374833583831787, "max": 8.252814292907715, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6778706876617488, "min": 1.5256820911639615, "max": 1.6844407586218084, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.10919807851315, "min": 144.7479979544878, "max": 179.28299815952778, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6778706876617488, "min": 1.5256820911639615, "max": 1.6844407586218084, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.10919807851315, "min": 144.7479979544878, "max": 179.28299815952778, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03439857924093652, "min": 0.03302704769602606, "max": 0.04004053215949649, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4054593448527157, "min": 3.3604384298814693, "max": 3.8646631520678056, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06978463777137141, "min": 0.06328786147019111, "max": 0.07277958452912225, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9769849287991996, "min": 0.8860300605826755, "max": 1.0189141834077116, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015989804025970954, "min": 0.014383297056372698, "max": 0.01814501826311116, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22385725636359338, "min": 0.20136615878921776, "max": 0.25403025568355625, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.9491847312571417e-06, "min": 2.9491847312571417e-06, "max": 5.6809395349276196e-05, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.1288586237599984e-05, "min": 4.1288586237599984e-05, "max": 0.0007953315348898667, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10098302857142857, "min": 0.10098302857142857, "max": 0.11893643809523811, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4137624, "min": 1.4137624, "max": 1.6947164, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010820455428571427, "min": 0.00010820455428571427, "max": 0.001901750165714286, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015148637599999998, "min": 0.0015148637599999998, "max": 0.026624502320000003, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011017878539860249, "min": 0.011017878539860249, "max": 0.012588911689817905, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15425029397010803, "min": 0.15425029397010803, "max": 0.17744432389736176, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707226400", "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 --resume", "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": "1707227207" }, "total": 806.2732335289984, "count": 1, "self": 0.8910804639963317, "children": { "run_training.setup": { "total": 0.05141686199931428, "count": 1, "self": 0.05141686199931428 }, "TrainerController.start_learning": { "total": 805.3307362030027, "count": 1, "self": 0.46869988587422995, "children": { "TrainerController._reset_env": { "total": 3.146004771002481, "count": 1, "self": 3.146004771002481 }, "TrainerController.advance": { "total": 801.5817962581277, "count": 19591, "self": 0.4727443762421899, "children": { "env_step": { "total": 600.9174299457518, "count": 19591, "self": 559.3715803716259, "children": { "SubprocessEnvManager._take_step": { "total": 41.26416852231341, "count": 19591, "self": 1.4689321469522838, "children": { "TorchPolicy.evaluate": { "total": 39.79523637536113, "count": 18807, "self": 39.79523637536113 } } }, "workers": { "total": 0.28168105181248393, "count": 19591, "self": 0.0, "children": { "worker_root": { "total": 803.286710146167, "count": 19591, "is_parallel": true, "self": 280.86225738438225, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003605023001000518, "count": 1, "is_parallel": true, "self": 0.0015925849984341767, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020124380025663413, "count": 8, "is_parallel": true, "self": 0.0020124380025663413 } } }, "UnityEnvironment.step": { "total": 0.04837222299829591, "count": 1, "is_parallel": true, "self": 0.0006892470009915996, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048676000005798414, "count": 1, "is_parallel": true, "self": 0.00048676000005798414 }, "communicator.exchange": { "total": 0.045473428999684984, "count": 1, "is_parallel": true, "self": 0.045473428999684984 }, "steps_from_proto": { "total": 0.001722786997561343, "count": 1, "is_parallel": true, "self": 0.0003736929938895628, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013490940036717802, "count": 8, "is_parallel": true, "self": 0.0013490940036717802 } } } } } } }, "UnityEnvironment.step": { "total": 522.4244527617848, "count": 19590, "is_parallel": true, "self": 11.239625618531136, "children": { "UnityEnvironment._generate_step_input": { "total": 7.690337222949893, "count": 19590, "is_parallel": true, "self": 7.690337222949893 }, "communicator.exchange": { "total": 471.39396040511565, "count": 19590, "is_parallel": true, "self": 471.39396040511565 }, "steps_from_proto": { "total": 32.1005295151881, "count": 19590, "is_parallel": true, "self": 6.561638478426175, "children": { "_process_rank_one_or_two_observation": { "total": 25.538891036761925, "count": 156720, "is_parallel": true, "self": 25.538891036761925 } } } } } } } } } } }, "trainer_advance": { "total": 200.19162193613374, "count": 19591, "self": 0.8928871070966125, "children": { "process_trajectory": { "total": 40.976483486043435, "count": 19591, "self": 40.77906962304405, "children": { "RLTrainer._checkpoint": { "total": 0.19741386299938313, "count": 1, "self": 0.19741386299938313 } } }, "_update_policy": { "total": 158.3222513429937, "count": 142, "self": 92.2830210679349, "children": { "TorchPPOOptimizer.update": { "total": 66.0392302750588, "count": 6828, "self": 66.0392302750588 } } } } } } }, "trainer_threads": { "total": 1.7079983081202954e-06, "count": 1, "self": 1.7079983081202954e-06 }, "TrainerController._save_models": { "total": 0.13423358000000007, "count": 1, "self": 0.004639612998289522, "children": { "RLTrainer._checkpoint": { "total": 0.12959396700171055, "count": 1, "self": 0.12959396700171055 } } } } } } }