{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16193443536758423, "min": 0.1470310539007187, "max": 1.4243311882019043, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4837.3056640625, "min": 4401.521484375, "max": 43208.51171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999936.0, "min": 29952.0, "max": 2999936.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999936.0, "min": 29952.0, "max": 2999936.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8124101758003235, "min": -0.10657144337892532, "max": 0.8732709288597107, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.28582763671875, "min": -25.577146530151367, "max": 269.0570068359375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024089064449071884, "min": -0.02345510944724083, "max": 0.4373529255390167, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.154452323913574, "min": -7.059988021850586, "max": 103.65264129638672, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06706983929720749, "min": 0.06336835239129694, "max": 0.07606475211520605, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9389777501609049, "min": 0.5324532648064424, "max": 1.0921458846994438, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016058613864255937, "min": 0.00016324549013938517, "max": 0.017302247981119546, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22482059409958313, "min": 0.0021221913718120072, "max": 0.2502352620843643, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4837066483214273e-06, "min": 1.4837066483214273e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.077189307649998e-05, "min": 2.077189307649998e-05, "max": 0.004011209062930333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049453571428571, "min": 0.10049453571428571, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069235, "min": 1.3962282666666668, "max": 2.737069666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.940411785714281e-05, "min": 5.940411785714281e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008316576499999993, "min": 0.0008316576499999993, "max": 0.13371325969999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008784917183220387, "min": 0.00857367180287838, "max": 0.6972795724868774, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12298883497714996, "min": 0.1215851902961731, "max": 4.880957126617432, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 216.98507462686567, "min": 205.5034965034965, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29076.0, "min": 15984.0, "max": 34027.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.783014908321758, "min": -1.0000000521540642, "max": 1.7906690025833292, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 238.92399771511555, "min": -31.99520167708397, "max": 257.1881980895996, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.783014908321758, "min": -1.0000000521540642, "max": 1.7906690025833292, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 238.92399771511555, "min": -31.99520167708397, "max": 257.1881980895996, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01970004268970563, "min": 0.01845037953280807, "max": 14.082473637536168, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6398057204205543, "min": 2.6384042731915542, "max": 225.3195782005787, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739125619", "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": "1739133301" }, "total": 7682.4071016200005, "count": 1, "self": 0.4786303829996541, "children": { "run_training.setup": { "total": 0.020335446999979467, "count": 1, "self": 0.020335446999979467 }, "TrainerController.start_learning": { "total": 7681.90813579, "count": 1, "self": 4.699181776844853, "children": { "TrainerController._reset_env": { "total": 2.091974930000106, "count": 1, "self": 2.091974930000106 }, "TrainerController.advance": { "total": 7675.024462956155, "count": 194637, "self": 4.6697821054976885, "children": { "env_step": { "total": 5555.153338391715, "count": 194637, "self": 5051.723275001214, "children": { "SubprocessEnvManager._take_step": { "total": 500.679025894774, "count": 194637, "self": 14.853310064700963, "children": { "TorchPolicy.evaluate": { "total": 485.825715830073, "count": 187559, "self": 485.825715830073 } } }, "workers": { "total": 2.7510374957278145, "count": 194637, "self": 0.0, "children": { "worker_root": { "total": 7664.868731438481, "count": 194637, "is_parallel": true, "self": 2985.058304433677, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022577550003006763, "count": 1, "is_parallel": true, "self": 0.0007944660001157899, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014632890001848864, "count": 8, "is_parallel": true, "self": 0.0014632890001848864 } } }, "UnityEnvironment.step": { "total": 0.04910021299974687, "count": 1, "is_parallel": true, "self": 0.000535524000042642, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004488569998102321, "count": 1, "is_parallel": true, "self": 0.0004488569998102321 }, "communicator.exchange": { "total": 0.04652477999979965, "count": 1, "is_parallel": true, "self": 0.04652477999979965 }, "steps_from_proto": { "total": 0.0015910520000943507, "count": 1, "is_parallel": true, "self": 0.000371924999399198, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012191270006951527, "count": 8, "is_parallel": true, "self": 0.0012191270006951527 } } } } } } }, "UnityEnvironment.step": { "total": 4679.810427004803, "count": 194636, "is_parallel": true, "self": 98.85430034067394, "children": { "UnityEnvironment._generate_step_input": { "total": 71.06373559605481, "count": 194636, "is_parallel": true, "self": 71.06373559605481 }, "communicator.exchange": { "total": 4210.4325776277765, "count": 194636, "is_parallel": true, "self": 4210.4325776277765 }, "steps_from_proto": { "total": 299.4598134402977, "count": 194636, "is_parallel": true, "self": 62.02341519566653, "children": { "_process_rank_one_or_two_observation": { "total": 237.43639824463116, "count": 1557088, "is_parallel": true, "self": 237.43639824463116 } } } } } } } } } } }, "trainer_advance": { "total": 2115.2013424589422, "count": 194637, "self": 9.173988797817401, "children": { "process_trajectory": { "total": 410.9667213651278, "count": 194637, "self": 410.36151667612967, "children": { "RLTrainer._checkpoint": { "total": 0.6052046889981284, "count": 6, "self": 0.6052046889981284 } } }, "_update_policy": { "total": 1695.060632295997, "count": 1398, "self": 924.5696014828495, "children": { "TorchPPOOptimizer.update": { "total": 770.4910308131475, "count": 68439, "self": 770.4910308131475 } } } } } } }, "trainer_threads": { "total": 8.610004442743957e-07, "count": 1, "self": 8.610004442743957e-07 }, "TrainerController._save_models": { "total": 0.09251526600019133, "count": 1, "self": 0.0014094159996602684, "children": { "RLTrainer._checkpoint": { "total": 0.09110585000053106, "count": 1, "self": 0.09110585000053106 } } } } } } }