{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45222407579421997, "min": 0.45031824707984924, "max": 1.458025336265564, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13545.015625, "min": 13545.015625, "max": 44230.65625, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29931.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29931.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.55757075548172, "min": -0.12418726086616516, "max": 0.55757075548172, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 153.8895263671875, "min": -29.92913055419922, "max": 153.8895263671875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025798780843615532, "min": 0.001230901456438005, "max": 0.47238585352897644, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.1204633712768555, "min": 0.3348051905632019, "max": 111.9554443359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06992846984455052, "min": 0.06374605744603043, "max": 0.0724483949298917, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0489270476682577, "min": 0.5795871594391336, "max": 1.0608616909251878, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016573755301780894, "min": 0.00046503534088704275, "max": 0.016573755301780894, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2486063295267134, "min": 0.005580424090644513, "max": 0.2486063295267134, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.434857521746671e-06, "min": 7.434857521746671e-06, "max": 0.000294759976746675, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011152286282620006, "min": 0.00011152286282620006, "max": 0.0034382088539303994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247825333333334, "min": 0.10247825333333334, "max": 0.19825332499999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371738000000001, "min": 1.4778601, "max": 2.4013907999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025757750800000013, "min": 0.00025757750800000013, "max": 0.0098255071675, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038636626200000018, "min": 0.0038636626200000018, "max": 0.11461235303999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008056205697357655, "min": 0.008000189438462257, "max": 0.36947691440582275, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1208430826663971, "min": 0.1120026558637619, "max": 2.955815315246582, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.3837209302326, "min": 345.3837209302326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29703.0, "min": 17369.0, "max": 32756.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5848302115188089, "min": -0.9999161809682846, "max": 1.5848302115188089, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.29539819061756, "min": -30.997401610016823, "max": 136.29539819061756, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5848302115188089, "min": -0.9999161809682846, "max": 1.5848302115188089, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.29539819061756, "min": -30.997401610016823, "max": 136.29539819061756, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.028647029895922927, "min": 0.028647029895922927, "max": 7.631950915687614, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4636445710493717, "min": 2.4636445710493717, "max": 137.37511648237705, "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": "1715259905", "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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715262276" }, "total": 2370.8327652850003, "count": 1, "self": 0.6457729829999153, "children": { "run_training.setup": { "total": 0.061939832999996725, "count": 1, "self": 0.061939832999996725 }, "TrainerController.start_learning": { "total": 2370.1250524690004, "count": 1, "self": 1.5321281059582361, "children": { "TrainerController._reset_env": { "total": 3.05153940699995, "count": 1, "self": 3.05153940699995 }, "TrainerController.advance": { "total": 2365.4493206580423, "count": 63758, "self": 1.5998393751065123, "children": { "env_step": { "total": 1695.7151448649677, "count": 63758, "self": 1547.7493479258965, "children": { "SubprocessEnvManager._take_step": { "total": 147.01777367603722, "count": 63758, "self": 5.452806942973552, "children": { "TorchPolicy.evaluate": { "total": 141.56496673306367, "count": 62553, "self": 141.56496673306367 } } }, "workers": { "total": 0.9480232630340879, "count": 63758, "self": 0.0, "children": { "worker_root": { "total": 2364.2101253830356, "count": 63758, "is_parallel": true, "self": 953.2112145269991, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005453439000007165, "count": 1, "is_parallel": true, "self": 0.0038916349999453814, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015618040000617839, "count": 8, "is_parallel": true, "self": 0.0015618040000617839 } } }, "UnityEnvironment.step": { "total": 0.05156149499998719, "count": 1, "is_parallel": true, "self": 0.0006632819997776096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047409300009348954, "count": 1, "is_parallel": true, "self": 0.00047409300009348954 }, "communicator.exchange": { "total": 0.048620781000067836, "count": 1, "is_parallel": true, "self": 0.048620781000067836 }, "steps_from_proto": { "total": 0.001803339000048254, "count": 1, "is_parallel": true, "self": 0.0003875419999985752, "children": { "_process_rank_one_or_two_observation": { "total": 0.001415797000049679, "count": 8, "is_parallel": true, "self": 0.001415797000049679 } } } } } } }, "UnityEnvironment.step": { "total": 1410.9989108560364, "count": 63757, "is_parallel": true, "self": 36.36750404308236, "children": { "UnityEnvironment._generate_step_input": { "total": 25.650035150041845, "count": 63757, "is_parallel": true, "self": 25.650035150041845 }, "communicator.exchange": { "total": 1239.847735687948, "count": 63757, "is_parallel": true, "self": 1239.847735687948 }, "steps_from_proto": { "total": 109.13363597496448, "count": 63757, "is_parallel": true, "self": 22.52969078999297, "children": { "_process_rank_one_or_two_observation": { "total": 86.60394518497151, "count": 510056, "is_parallel": true, "self": 86.60394518497151 } } } } } } } } } } }, "trainer_advance": { "total": 668.1343364179681, "count": 63758, "self": 2.932238520954911, "children": { "process_trajectory": { "total": 141.7804977120079, "count": 63758, "self": 141.50903334600775, "children": { "RLTrainer._checkpoint": { "total": 0.2714643660001457, "count": 2, "self": 0.2714643660001457 } } }, "_update_policy": { "total": 523.4216001850053, "count": 450, "self": 308.91229263299306, "children": { "TorchPPOOptimizer.update": { "total": 214.50930755201227, "count": 22761, "self": 214.50930755201227 } } } } } } }, "trainer_threads": { "total": 9.089999366551638e-07, "count": 1, "self": 9.089999366551638e-07 }, "TrainerController._save_models": { "total": 0.09206338900003175, "count": 1, "self": 0.0014889880003465805, "children": { "RLTrainer._checkpoint": { "total": 0.09057440099968517, "count": 1, "self": 0.09057440099968517 } } } } } } }