{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2930396795272827, "min": 0.2910306751728058, "max": 0.3772023618221283, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 8809.9453125, "min": 8684.35546875, "max": 11434.484375, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 248.008547008547, "min": 235.304, "max": 285.65346534653463, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29017.0, "min": 28296.0, "max": 31390.0, "count": 16 }, "Pyramids.Step.mean": { "value": 1979990.0, "min": 1529895.0, "max": 1979990.0, "count": 16 }, "Pyramids.Step.sum": { "value": 1979990.0, "min": 1529895.0, "max": 1979990.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7462483048439026, "min": 0.6567258238792419, "max": 0.8047998547554016, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 219.39700317382812, "min": 187.82357788085938, "max": 243.049560546875, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00307209393940866, "min": -0.03147309273481369, "max": 0.010138324461877346, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.9031956195831299, "min": -9.158669471740723, "max": 2.970529079437256, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7343880247611265, "min": 1.6473124828189611, "max": 1.7646959874629975, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 202.9233988970518, "min": 173.14899863302708, "max": 220.58699843287468, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7343880247611265, "min": 1.6473124828189611, "max": 1.7646959874629975, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 202.9233988970518, "min": 173.14899863302708, "max": 220.58699843287468, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019553067057908904, "min": 0.01902993065235205, "max": 0.024178172263678528, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2877088457753416, "min": 2.2583879788508057, "max": 2.7079552935319953, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07168206840263437, "min": 0.06593017768768947, "max": 0.07168206840263437, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0035489576368812, "min": 0.9230224876276526, "max": 1.0545541316775295, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01512822743656221, "min": 0.012747654476932171, "max": 0.016180382961811988, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21179518411187093, "min": 0.1784671626770504, "max": 0.23259178962325677, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.252037535067855e-06, "min": 5.252037535067855e-06, "max": 7.26182043653857e-05, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.352852549094997e-05, "min": 7.352852549094997e-05, "max": 0.0010166548611153998, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10175064642857147, "min": 0.10175064642857147, "max": 0.12420604285714287, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4245090500000006, "min": 1.4245090500000006, "max": 1.7511241999999998, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018488957821428565, "min": 0.00018488957821428565, "max": 0.0024281836814285715, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.002588454094999999, "min": 0.002588454094999999, "max": 0.033994571540000004, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007591236382722855, "min": 0.007591236382722855, "max": 0.008284117095172405, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10627730935811996, "min": 0.10627730935811996, "max": 0.12192925065755844, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717187613", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717188961" }, "total": 1347.8709488369996, "count": 1, "self": 0.71397220200015, "children": { "run_training.setup": { "total": 0.07585502799975075, "count": 1, "self": 0.07585502799975075 }, "TrainerController.start_learning": { "total": 1347.0811216069997, "count": 1, "self": 0.7859482171006675, "children": { "TrainerController._reset_env": { "total": 3.318750089999412, "count": 1, "self": 3.318750089999412 }, "TrainerController.advance": { "total": 1342.8850223249, "count": 32833, "self": 0.8270375527827127, "children": { "env_step": { "total": 1011.166429489117, "count": 32833, "self": 939.4118349392274, "children": { "SubprocessEnvManager._take_step": { "total": 71.27514389595308, "count": 32833, "self": 2.551690115922611, "children": { "TorchPolicy.evaluate": { "total": 68.72345378003047, "count": 31306, "self": 68.72345378003047 } } }, "workers": { "total": 0.4794506539365102, "count": 32833, "self": 0.0, "children": { "worker_root": { "total": 1344.0018025109757, "count": 32833, "is_parallel": true, "self": 473.5056941710782, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002649463999659929, "count": 1, "is_parallel": true, "self": 0.0006987379993006471, "children": { "_process_rank_one_or_two_observation": { "total": 0.001950726000359282, "count": 8, "is_parallel": true, "self": 0.001950726000359282 } } }, "UnityEnvironment.step": { "total": 0.04991982699993969, "count": 1, "is_parallel": true, "self": 0.0006471659999078838, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005179090003366582, "count": 1, "is_parallel": true, "self": 0.0005179090003366582 }, "communicator.exchange": { "total": 0.04695517700019991, "count": 1, "is_parallel": true, "self": 0.04695517700019991 }, "steps_from_proto": { "total": 0.0017995749994952348, "count": 1, "is_parallel": true, "self": 0.00038207599936868064, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014174990001265542, "count": 8, "is_parallel": true, "self": 0.0014174990001265542 } } } } } } }, "UnityEnvironment.step": { "total": 870.4961083398975, "count": 32832, "is_parallel": true, "self": 17.881733952148352, "children": { "UnityEnvironment._generate_step_input": { "total": 12.423186172025453, "count": 32832, "is_parallel": true, "self": 12.423186172025453 }, "communicator.exchange": { "total": 786.9438411908104, "count": 32832, "is_parallel": true, "self": 786.9438411908104 }, "steps_from_proto": { "total": 53.247347024913324, "count": 32832, "is_parallel": true, "self": 11.437223629844084, "children": { "_process_rank_one_or_two_observation": { "total": 41.81012339506924, "count": 262656, "is_parallel": true, "self": 41.81012339506924 } } } } } } } } } } }, "trainer_advance": { "total": 330.89155528300034, "count": 32833, "self": 1.5352185120564172, "children": { "process_trajectory": { "total": 70.02132520893792, "count": 32833, "self": 69.90206173393835, "children": { "RLTrainer._checkpoint": { "total": 0.11926347499957046, "count": 1, "self": 0.11926347499957046 } } }, "_update_policy": { "total": 259.335011562006, "count": 237, "self": 153.22781376003695, "children": { "TorchPPOOptimizer.update": { "total": 106.10719780196905, "count": 11400, "self": 106.10719780196905 } } } } } } }, "trainer_threads": { "total": 9.87999555945862e-07, "count": 1, "self": 9.87999555945862e-07 }, "TrainerController._save_models": { "total": 0.09139998699993157, "count": 1, "self": 0.0019656249996842234, "children": { "RLTrainer._checkpoint": { "total": 0.08943436200024735, "count": 1, "self": 0.08943436200024735 } } } } } } }