{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4144514203071594, "min": 0.3985368609428406, "max": 1.4684513807296753, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12506.486328125, "min": 11688.2890625, "max": 44546.94140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29953.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29953.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6314187049865723, "min": -0.11818081140518188, "max": 0.6545875072479248, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.69149780273438, "min": -28.48157501220703, "max": 187.86660766601562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016399478539824486, "min": 0.008780745789408684, "max": 0.45667171478271484, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.64105224609375, "min": 2.4322664737701416, "max": 108.6878662109375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06818691839302023, "min": 0.06371709582004052, "max": 0.07284691916820342, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9546168575022831, "min": 0.4985615048922489, "max": 1.0601195945346262, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012970937485313428, "min": 0.0014985303531402582, "max": 0.015495542700810707, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.181593124794388, "min": 0.0179823642376831, "max": 0.2169375978113499, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.63310459852143e-06, "min": 7.63310459852143e-06, "max": 0.00029523835873007144, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010686346437930001, "min": 0.00010686346437930001, "max": 0.0035085032304989993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254433571428571, "min": 0.10254433571428571, "max": 0.1984127857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356207, "min": 1.3888894999999999, "max": 2.5725670000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002641791378571429, "min": 0.0002641791378571429, "max": 0.009841437292857141, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036985079300000004, "min": 0.0036985079300000004, "max": 0.11697314990000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016564244404435158, "min": 0.016564244404435158, "max": 0.49161505699157715, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2318994253873825, "min": 0.2318994253873825, "max": 3.44130539894104, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 316.88775510204084, "min": 285.92929292929296, "max": 997.53125, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31055.0, "min": 16624.0, "max": 33326.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6002865775497919, "min": -0.935975051485002, "max": 1.693846135830077, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 155.2277980223298, "min": -29.951201647520065, "max": 176.159998126328, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6002865775497919, "min": -0.935975051485002, "max": 1.693846135830077, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 155.2277980223298, "min": -29.951201647520065, "max": 176.159998126328, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05402049765254241, "min": 0.050719526417546706, "max": 8.996790203758898, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.239988272296614, "min": 5.239988272296614, "max": 152.94543346390128, "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": "1735212323", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/root/miniconda3/envs/drl/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": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1735214004" }, "total": 1680.670391683001, "count": 1, "self": 0.4254881340002612, "children": { "run_training.setup": { "total": 0.019970421000834904, "count": 1, "self": 0.019970421000834904 }, "TrainerController.start_learning": { "total": 1680.224933128, "count": 1, "self": 1.5054377173928515, "children": { "TrainerController._reset_env": { "total": 2.779871639000703, "count": 1, "self": 2.779871639000703 }, "TrainerController.advance": { "total": 1675.883274325608, "count": 64064, "self": 1.381713809663779, "children": { "env_step": { "total": 1127.1912900658826, "count": 64064, "self": 1027.8975822431948, "children": { "SubprocessEnvManager._take_step": { "total": 98.3637272759297, "count": 64064, "self": 4.188780534972466, "children": { "TorchPolicy.evaluate": { "total": 94.17494674095724, "count": 62560, "self": 94.17494674095724 } } }, "workers": { "total": 0.9299805467580882, "count": 64064, "self": 0.0, "children": { "worker_root": { "total": 1677.2472033449922, "count": 64064, "is_parallel": true, "self": 746.3455787602197, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001806935000786325, "count": 1, "is_parallel": true, "self": 0.0006566000010934658, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011503349996928591, "count": 8, "is_parallel": true, "self": 0.0011503349996928591 } } }, "UnityEnvironment.step": { "total": 0.032826308999574394, "count": 1, "is_parallel": true, "self": 0.0002168909977626754, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000186282000868232, "count": 1, "is_parallel": true, "self": 0.000186282000868232 }, "communicator.exchange": { "total": 0.03172265899956983, "count": 1, "is_parallel": true, "self": 0.03172265899956983 }, "steps_from_proto": { "total": 0.0007004770013736561, "count": 1, "is_parallel": true, "self": 0.0001693459998932667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005311310014803894, "count": 8, "is_parallel": true, "self": 0.0005311310014803894 } } } } } } }, "UnityEnvironment.step": { "total": 930.9016245847724, "count": 64063, "is_parallel": true, "self": 17.117365205596798, "children": { "UnityEnvironment._generate_step_input": { "total": 15.384941251100827, "count": 64063, "is_parallel": true, "self": 15.384941251100827 }, "communicator.exchange": { "total": 850.457982580896, "count": 64063, "is_parallel": true, "self": 850.457982580896 }, "steps_from_proto": { "total": 47.941335547178824, "count": 64063, "is_parallel": true, "self": 11.881226216675714, "children": { "_process_rank_one_or_two_observation": { "total": 36.06010933050311, "count": 512504, "is_parallel": true, "self": 36.06010933050311 } } } } } } } } } } }, "trainer_advance": { "total": 547.3102704500616, "count": 64064, "self": 2.86327053792229, "children": { "process_trajectory": { "total": 89.21897123414237, "count": 64064, "self": 89.01653165714379, "children": { "RLTrainer._checkpoint": { "total": 0.20243957699858584, "count": 2, "self": 0.20243957699858584 } } }, "_update_policy": { "total": 455.2280286779969, "count": 454, "self": 213.1935840078113, "children": { "TorchPPOOptimizer.update": { "total": 242.03444467018562, "count": 22773, "self": 242.03444467018562 } } } } } } }, "trainer_threads": { "total": 1.0449984984006733e-06, "count": 1, "self": 1.0449984984006733e-06 }, "TrainerController._save_models": { "total": 0.05634840099992289, "count": 1, "self": 0.0026531379990046844, "children": { "RLTrainer._checkpoint": { "total": 0.0536952630009182, "count": 1, "self": 0.0536952630009182 } } } } } } }