{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.556074857711792, "min": 0.5189160108566284, "max": 1.4152575731277466, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16735.62890625, "min": 15575.7822265625, "max": 42933.25390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989926.0, "min": 29952.0, "max": 989926.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3231457769870758, "min": -0.09028290212154388, "max": 0.40994125604629517, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.37161254882812, "min": -21.7581787109375, "max": 109.04437255859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.15478551387786865, "min": -0.04441161826252937, "max": 0.32533353567123413, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 39.934661865234375, "min": -11.769079208374023, "max": 77.10404968261719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06734742322130062, "min": 0.0658544599793105, "max": 0.07334267806795018, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9428639250982087, "min": 0.4819281540052355, "max": 1.0874083324874222, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015342905308075605, "min": 0.00044601225354061024, "max": 0.015342905308075605, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21480067431305847, "min": 0.004014110281865492, "max": 0.21480067431305847, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.527247490950001e-06, "min": 7.527247490950001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010538146487330001, "min": 0.00010538146487330001, "max": 0.0032578070140643995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250904999999999, "min": 0.10250904999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351266999999999, "min": 1.3886848, "max": 2.4854804000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002606540950000001, "min": 0.0002606540950000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003649157330000001, "min": 0.003649157330000001, "max": 0.10861496643999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008008499629795551, "min": 0.007513976190239191, "max": 0.35842666029930115, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11211898922920227, "min": 0.10519566386938095, "max": 2.508986711502075, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 469.8333333333333, "min": 427.8805970149254, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28190.0, "min": 15984.0, "max": 32635.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.296753314634164, "min": -1.0000000521540642, "max": 1.4104060294727485, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.80519887804985, "min": -30.999801620841026, "max": 93.0867979452014, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.296753314634164, "min": -1.0000000521540642, "max": 1.4104060294727485, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.80519887804985, "min": -30.999801620841026, "max": 93.0867979452014, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03884969209611881, "min": 0.03361511268716396, "max": 6.862451239489019, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.330981525767129, "min": 2.252212550039985, "max": 109.7992198318243, "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": "1739942200", "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": "1739944335" }, "total": 2135.3108168579997, "count": 1, "self": 0.4786771819999558, "children": { "run_training.setup": { "total": 0.020273017999898002, "count": 1, "self": 0.020273017999898002 }, "TrainerController.start_learning": { "total": 2134.811866658, "count": 1, "self": 1.2737862969393063, "children": { "TrainerController._reset_env": { "total": 2.11461128000019, "count": 1, "self": 2.11461128000019 }, "TrainerController.advance": { "total": 2131.3402280450605, "count": 63534, "self": 1.3382510441265367, "children": { "env_step": { "total": 1462.1007021569324, "count": 63534, "self": 1309.0528204849898, "children": { "SubprocessEnvManager._take_step": { "total": 152.3123549129557, "count": 63534, "self": 4.611316066945847, "children": { "TorchPolicy.evaluate": { "total": 147.70103884600985, "count": 62580, "self": 147.70103884600985 } } }, "workers": { "total": 0.7355267589869072, "count": 63534, "self": 0.0, "children": { "worker_root": { "total": 2129.8802617060014, "count": 63534, "is_parallel": true, "self": 930.4608521190307, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020028980000006413, "count": 1, "is_parallel": true, "self": 0.0006799010000122507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013229969999883906, "count": 8, "is_parallel": true, "self": 0.0013229969999883906 } } }, "UnityEnvironment.step": { "total": 0.04636021200008145, "count": 1, "is_parallel": true, "self": 0.000577382999836118, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045105800018063746, "count": 1, "is_parallel": true, "self": 0.00045105800018063746 }, "communicator.exchange": { "total": 0.04375637599991933, "count": 1, "is_parallel": true, "self": 0.04375637599991933 }, "steps_from_proto": { "total": 0.0015753950001453632, "count": 1, "is_parallel": true, "self": 0.00034536099997239944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012300340001729637, "count": 8, "is_parallel": true, "self": 0.0012300340001729637 } } } } } } }, "UnityEnvironment.step": { "total": 1199.4194095869707, "count": 63533, "is_parallel": true, "self": 31.170201679043203, "children": { "UnityEnvironment._generate_step_input": { "total": 23.024817638996637, "count": 63533, "is_parallel": true, "self": 23.024817638996637 }, "communicator.exchange": { "total": 1049.8821155520054, "count": 63533, "is_parallel": true, "self": 1049.8821155520054 }, "steps_from_proto": { "total": 95.34227471692543, "count": 63533, "is_parallel": true, "self": 19.12196684779269, "children": { "_process_rank_one_or_two_observation": { "total": 76.22030786913274, "count": 508264, "is_parallel": true, "self": 76.22030786913274 } } } } } } } } } } }, "trainer_advance": { "total": 667.9012748440016, "count": 63534, "self": 2.3925718549912744, "children": { "process_trajectory": { "total": 124.40328916200974, "count": 63534, "self": 124.20000501100935, "children": { "RLTrainer._checkpoint": { "total": 0.2032841510003891, "count": 2, "self": 0.2032841510003891 } } }, "_update_policy": { "total": 541.1054138270006, "count": 445, "self": 296.499136437006, "children": { "TorchPPOOptimizer.update": { "total": 244.6062773899946, "count": 22797, "self": 244.6062773899946 } } } } } } }, "trainer_threads": { "total": 9.989998943638057e-07, "count": 1, "self": 9.989998943638057e-07 }, "TrainerController._save_models": { "total": 0.08324003699999594, "count": 1, "self": 0.001445833000161656, "children": { "RLTrainer._checkpoint": { "total": 0.08179420399983428, "count": 1, "self": 0.08179420399983428 } } } } } } }