{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.961172342300415, "min": 0.9050999879837036, "max": 1.5976853370666504, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 28635.24609375, "min": 27109.5546875, "max": 48467.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989976.0, "min": 29952.0, "max": 989976.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989976.0, "min": 29952.0, "max": 989976.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04595477506518364, "min": -0.09698932617902756, "max": 0.06372394412755966, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -11.121055603027344, "min": -23.27743911743164, "max": 15.102574348449707, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027481788769364357, "min": 0.027325795963406563, "max": 0.7620301246643066, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.650592803955078, "min": 6.612842559814453, "max": 180.60113525390625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0667391515467205, "min": 0.0667391515467205, "max": 0.07425242114836991, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.4671740608270435, "min": 0.2755218757544989, "max": 0.5653445163445534, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007047905578127982, "min": 0.0004799619620978361, "max": 0.07719916712139147, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.049335339046895875, "min": 0.003359733734684853, "max": 0.30879666848556586, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.5663402909000014e-06, "min": 2.5663402909000014e-06, "max": 9.84832015168e-05, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.796438203630001e-05, "min": 1.796438203630001e-05, "max": 0.0006062857937143, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.09999999999999999, "min": 0.09999999999999998, "max": 0.09999999999999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.7, "min": 0.3999999999999999, "max": 0.7999999999999999, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002663676614285715, "min": 0.0002663676614285715, "max": 0.009848471680000002, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0018645736300000007, "min": 0.0018645736300000007, "max": 0.06063794143, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.026587823405861855, "min": 0.026587823405861855, "max": 0.6488816142082214, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18611475825309753, "min": 0.18611475825309753, "max": 2.5955264568328857, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 928.65625, "min": 866.8857142857142, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29717.0, "min": 15984.0, "max": 33226.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.4915500492788851, "min": -1.0000000521540642, "max": -0.2024937877431512, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.729601576924324, "min": -32.000001668930054, "max": -6.479801207780838, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.4915500492788851, "min": -1.0000000521540642, "max": -0.2024937877431512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.729601576924324, "min": -32.000001668930054, "max": -6.479801207780838, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.2542322325607529, "min": 0.2542322325607529, "max": 17.90512027591467, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 8.135431441944093, "min": 8.135431441944093, "max": 286.4819244146347, "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": "1704689910", "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 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704691942" }, "total": 2032.2205313619997, "count": 1, "self": 0.4987475669995547, "children": { "run_training.setup": { "total": 0.047541095000269706, "count": 1, "self": 0.047541095000269706 }, "TrainerController.start_learning": { "total": 2031.6742427, "count": 1, "self": 1.317536082062361, "children": { "TrainerController._reset_env": { "total": 1.9400066570005947, "count": 1, "self": 1.9400066570005947 }, "TrainerController.advance": { "total": 2028.3313080169382, "count": 63173, "self": 1.396747711027274, "children": { "env_step": { "total": 1390.3275136758148, "count": 63173, "self": 1260.4395597069297, "children": { "SubprocessEnvManager._take_step": { "total": 129.09048500895642, "count": 63173, "self": 4.6588322839161265, "children": { "TorchPolicy.evaluate": { "total": 124.4316527250403, "count": 62557, "self": 124.4316527250403 } } }, "workers": { "total": 0.7974689599286648, "count": 63173, "self": 0.0, "children": { "worker_root": { "total": 2026.8043625139117, "count": 63173, "is_parallel": true, "self": 882.6443984438802, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017154540000774432, "count": 1, "is_parallel": true, "self": 0.0005335519990694593, "children": { "_process_rank_one_or_two_observation": { "total": 0.001181902001007984, "count": 8, "is_parallel": true, "self": 0.001181902001007984 } } }, "UnityEnvironment.step": { "total": 0.04980530399916461, "count": 1, "is_parallel": true, "self": 0.0005684169982487219, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048150800012081163, "count": 1, "is_parallel": true, "self": 0.00048150800012081163 }, "communicator.exchange": { "total": 0.047169911000310094, "count": 1, "is_parallel": true, "self": 0.047169911000310094 }, "steps_from_proto": { "total": 0.0015854680004849797, "count": 1, "is_parallel": true, "self": 0.00035293000019009924, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012325380002948805, "count": 8, "is_parallel": true, "self": 0.0012325380002948805 } } } } } } }, "UnityEnvironment.step": { "total": 1144.1599640700315, "count": 63172, "is_parallel": true, "self": 34.53466255487183, "children": { "UnityEnvironment._generate_step_input": { "total": 24.920309795097637, "count": 63172, "is_parallel": true, "self": 24.920309795097637 }, "communicator.exchange": { "total": 985.0506505090198, "count": 63172, "is_parallel": true, "self": 985.0506505090198 }, "steps_from_proto": { "total": 99.65434121104227, "count": 63172, "is_parallel": true, "self": 20.039138551112046, "children": { "_process_rank_one_or_two_observation": { "total": 79.61520265993022, "count": 505376, "is_parallel": true, "self": 79.61520265993022 } } } } } } } } } } }, "trainer_advance": { "total": 636.6070466300962, "count": 63173, "self": 2.4303908310939732, "children": { "process_trajectory": { "total": 123.72575777099792, "count": 63173, "self": 123.52332185499836, "children": { "RLTrainer._checkpoint": { "total": 0.20243591599955835, "count": 2, "self": 0.20243591599955835 } } }, "_update_policy": { "total": 510.4508980280043, "count": 229, "self": 303.8662957599654, "children": { "TorchPPOOptimizer.update": { "total": 206.5846022680389, "count": 23142, "self": 206.5846022680389 } } } } } } }, "trainer_threads": { "total": 9.419991329195909e-07, "count": 1, "self": 9.419991329195909e-07 }, "TrainerController._save_models": { "total": 0.08539100199959648, "count": 1, "self": 0.0013977210001030471, "children": { "RLTrainer._checkpoint": { "total": 0.08399328099949344, "count": 1, "self": 0.08399328099949344 } } } } } } }