{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6366585493087769, "min": 0.6366585493087769, "max": 0.6978288888931274, "count": 2 }, "Pyramids.Policy.Entropy.sum": { "value": 19232.181640625, "min": 14659.9892578125, "max": 19232.181640625, "count": 2 }, "Pyramids.Step.mean": { "value": 1049927.0, "min": 1019897.0, "max": 1049927.0, "count": 2 }, "Pyramids.Step.sum": { "value": 1049927.0, "min": 1019897.0, "max": 1049927.0, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.40033647418022156, "min": 0.29243791103363037, "max": 0.40033647418022156, "count": 2 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 106.489501953125, "min": 51.46907043457031, "max": 106.489501953125, "count": 2 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016297506168484688, "min": 0.016297506168484688, "max": 0.02224510908126831, "count": 2 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.335136413574219, "min": 3.9151391983032227, "max": 4.335136413574219, "count": 2 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 434.9178082191781, "min": 434.9178082191781, "max": 459.70588235294116, "count": 2 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31749.0, "min": 15630.0, "max": 31749.0, "count": 2 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4280520266253653, "min": 1.4280520266253653, "max": 1.4814411583630478, "count": 2 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 104.24779794365168, "min": 50.368999384343624, "max": 104.24779794365168, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4280520266253653, "min": 1.4280520266253653, "max": 1.4814411583630478, "count": 2 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 104.24779794365168, "min": 50.368999384343624, "max": 104.24779794365168, "count": 2 }, "Pyramids.Policy.RndReward.mean": { "value": 0.043881038365501286, "min": 0.043881038365501286, "max": 0.0459491216153016, "count": 2 }, "Pyramids.Policy.RndReward.sum": { "value": 3.203315800681594, "min": 1.5622701349202543, "max": 3.203315800681594, "count": 2 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07294199608098577, "min": 0.06984487097361125, "max": 0.07294199608098577, "count": 2 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0211879451338008, "min": 0.6286038387625013, "max": 1.0211879451338008, "count": 2 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013773114051030206, "min": 0.011432988577426943, "max": 0.013773114051030206, "count": 2 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19282359671442287, "min": 0.10289689719684249, "max": 0.19282359671442287, "count": 2 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019649318450228336, "min": 0.00019649318450228336, "max": 0.00019894616701795557, "count": 2 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002750904583031967, "min": 0.0017905155031616002, "max": 0.002750904583031967, "count": 2 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16549771666666668, "min": 0.16549771666666668, "max": 0.16631537777777783, "count": 2 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3169680333333336, "min": 1.4968384000000003, "max": 2.3169680333333336, "count": 2 }, "Pyramids.Policy.Beta.mean": { "value": 0.006553221895000001, "min": 0.006553221895000001, "max": 0.00663490624, "count": 2 }, "Pyramids.Policy.Beta.sum": { "value": 0.09174510653000001, "min": 0.059714156160000004, "max": 0.09174510653000001, "count": 2 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009683212265372276, "min": 0.00955230463296175, "max": 0.009683212265372276, "count": 2 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13556496798992157, "min": 0.08597074449062347, "max": 0.13556496798992157, "count": 2 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744718514", "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 --resume", "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": "1744718640" }, "total": 126.24376586700009, "count": 1, "self": 0.3855377270006102, "children": { "run_training.setup": { "total": 0.02710945199987691, "count": 1, "self": 0.02710945199987691 }, "TrainerController.start_learning": { "total": 125.8311186879996, "count": 1, "self": 0.07734110102410341, "children": { "TrainerController._reset_env": { "total": 2.4028737109997564, "count": 1, "self": 2.4028737109997564 }, "TrainerController.advance": { "total": 123.20777551997526, "count": 3505, "self": 0.07917219694081723, "children": { "env_step": { "total": 86.67971610301174, "count": 3505, "self": 78.064140476999, "children": { "SubprocessEnvManager._take_step": { "total": 8.571851791015433, "count": 3505, "self": 0.2591857140114371, "children": { "TorchPolicy.evaluate": { "total": 8.312666077003996, "count": 3413, "self": 8.312666077003996 } } }, "workers": { "total": 0.043723834997308586, "count": 3504, "self": 0.0, "children": { "worker_root": { "total": 125.40931257698503, "count": 3504, "is_parallel": true, "self": 53.83079038999358, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002085446999899432, "count": 1, "is_parallel": true, "self": 0.0007063649995870946, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013790820003123372, "count": 8, "is_parallel": true, "self": 0.0013790820003123372 } } }, "UnityEnvironment.step": { "total": 0.058076186000107555, "count": 1, "is_parallel": true, "self": 0.0005263969997031381, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048460600010002963, "count": 1, "is_parallel": true, "self": 0.00048460600010002963 }, "communicator.exchange": { "total": 0.05544696600009047, "count": 1, "is_parallel": true, "self": 0.05544696600009047 }, "steps_from_proto": { "total": 0.0016182170002139173, "count": 1, "is_parallel": true, "self": 0.0003581669998311554, "children": { "_process_rank_one_or_two_observation": { "total": 0.001260050000382762, "count": 8, "is_parallel": true, "self": 0.001260050000382762 } } } } } } }, "UnityEnvironment.step": { "total": 71.57852218699145, "count": 3503, "is_parallel": true, "self": 1.7317390100033663, "children": { "UnityEnvironment._generate_step_input": { "total": 1.2812941649726781, "count": 3503, "is_parallel": true, "self": 1.2812941649726781 }, "communicator.exchange": { "total": 63.20532393899157, "count": 3503, "is_parallel": true, "self": 63.20532393899157 }, "steps_from_proto": { "total": 5.360165073023836, "count": 3503, "is_parallel": true, "self": 1.0846400800387528, "children": { "_process_rank_one_or_two_observation": { "total": 4.275524992985083, "count": 28024, "is_parallel": true, "self": 4.275524992985083 } } } } } } } } } } }, "trainer_advance": { "total": 36.4488872200227, "count": 3504, "self": 0.1492938290134589, "children": { "process_trajectory": { "total": 7.362697597009628, "count": 3504, "self": 7.216756779009302, "children": { "RLTrainer._checkpoint": { "total": 0.14594081800032654, "count": 1, "self": 0.14594081800032654 } } }, "_update_policy": { "total": 28.93689579399961, "count": 25, "self": 15.80463261400746, "children": { "TorchPPOOptimizer.update": { "total": 13.132263179992151, "count": 1203, "self": 13.132263179992151 } } } } } } }, "trainer_threads": { "total": 1.4140005077933893e-06, "count": 1, "self": 1.4140005077933893e-06 }, "TrainerController._save_models": { "total": 0.14312694199998077, "count": 1, "self": 0.0020803480001632124, "children": { "RLTrainer._checkpoint": { "total": 0.14104659399981756, "count": 1, "self": 0.14104659399981756 } } } } } } }