{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12892360985279083, "min": 0.1215721145272255, "max": 1.3557578325271606, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3849.143310546875, "min": 3647.163330078125, "max": 41128.26953125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999922.0, "min": 29898.0, "max": 2999922.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999922.0, "min": 29898.0, "max": 2999922.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7925044298171997, "min": -0.09550029039382935, "max": 0.8931336402893066, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 236.95883178710938, "min": -23.01556968688965, "max": 273.17584228515625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010758834891021252, "min": -0.08753448724746704, "max": 0.386795312166214, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.2168915271759033, "min": -22.058691024780273, "max": 91.67048645019531, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06848765789221962, "min": 0.06350920135193365, "max": 0.07449852871237643, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9588272104910747, "min": 0.4744383845218703, "max": 1.073822987147187, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013585168394788598, "min": 0.00038379569667890953, "max": 0.016694437838547554, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19019235752704036, "min": 0.003454161270110186, "max": 0.23372212973966575, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4560066575547615e-06, "min": 1.4560066575547615e-06, "max": 0.00029841174338656194, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0384093205766662e-05, "min": 2.0384093205766662e-05, "max": 0.0039693416768861334, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048530238095237, "min": 0.10048530238095237, "max": 0.19947058095238096, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067942333333332, "min": 1.3962940666666668, "max": 2.737598366666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.848170785714286e-05, "min": 5.848170785714286e-05, "max": 0.009947111037142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008187439100000001, "min": 0.0008187439100000001, "max": 0.13231907528, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0064279548823833466, "min": 0.006295084487646818, "max": 0.48187491297721863, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08999136835336685, "min": 0.08813118189573288, "max": 3.373124361038208, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 214.1578947368421, "min": 195.17880794701986, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28483.0, "min": 16697.0, "max": 32536.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.770919383350593, "min": -0.999962551984936, "max": 1.7926978290938644, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 237.30319736897945, "min": -31.998801663517952, "max": 272.3171975016594, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.770919383350593, "min": -0.999962551984936, "max": 1.7926978290938644, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 237.30319736897945, "min": -31.998801663517952, "max": 272.3171975016594, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014109039775277454, "min": 0.013696996541424696, "max": 9.172356058569516, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8906113298871787, "min": 1.8906113298871787, "max": 155.93005299568176, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701702007", "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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701709218" }, "total": 7211.203173568, "count": 1, "self": 0.6457822100010162, "children": { "run_training.setup": { "total": 0.05269439299991063, "count": 1, "self": 0.05269439299991063 }, "TrainerController.start_learning": { "total": 7210.504696964999, "count": 1, "self": 3.9923694331610022, "children": { "TrainerController._reset_env": { "total": 3.0627412639998965, "count": 1, "self": 3.0627412639998965 }, "TrainerController.advance": { "total": 7203.347211178837, "count": 195173, "self": 4.071902204720573, "children": { "env_step": { "total": 5351.746946869085, "count": 195173, "self": 4979.025988699417, "children": { "SubprocessEnvManager._take_step": { "total": 370.22445013274523, "count": 195173, "self": 13.690965204720214, "children": { "TorchPolicy.evaluate": { "total": 356.533484928025, "count": 187549, "self": 356.533484928025 } } }, "workers": { "total": 2.4965080369229327, "count": 195173, "self": 0.0, "children": { "worker_root": { "total": 7197.187088753915, "count": 195173, "is_parallel": true, "self": 2562.168583248931, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019861499999933585, "count": 1, "is_parallel": true, "self": 0.0006163550003748242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013697949996185343, "count": 8, "is_parallel": true, "self": 0.0013697949996185343 } } }, "UnityEnvironment.step": { "total": 0.09139408700002605, "count": 1, "is_parallel": true, "self": 0.0006452439999975468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045229000011204334, "count": 1, "is_parallel": true, "self": 0.00045229000011204334 }, "communicator.exchange": { "total": 0.08871684399991864, "count": 1, "is_parallel": true, "self": 0.08871684399991864 }, "steps_from_proto": { "total": 0.0015797089999978198, "count": 1, "is_parallel": true, "self": 0.00032636000037200574, "children": { "_process_rank_one_or_two_observation": { "total": 0.001253348999625814, "count": 8, "is_parallel": true, "self": 0.001253348999625814 } } } } } } }, "UnityEnvironment.step": { "total": 4635.018505504984, "count": 195172, "is_parallel": true, "self": 102.40685103182113, "children": { "UnityEnvironment._generate_step_input": { "total": 71.16754488206175, "count": 195172, "is_parallel": true, "self": 71.16754488206175 }, "communicator.exchange": { "total": 4168.895824303004, "count": 195172, "is_parallel": true, "self": 4168.895824303004 }, "steps_from_proto": { "total": 292.54828528809776, "count": 195172, "is_parallel": true, "self": 57.60247175311838, "children": { "_process_rank_one_or_two_observation": { "total": 234.94581353497938, "count": 1561376, "is_parallel": true, "self": 234.94581353497938 } } } } } } } } } } }, "trainer_advance": { "total": 1847.5283621050312, "count": 195173, "self": 8.09876412478252, "children": { "process_trajectory": { "total": 377.81025067125415, "count": 195173, "self": 377.1727975502547, "children": { "RLTrainer._checkpoint": { "total": 0.637453120999453, "count": 6, "self": 0.637453120999453 } } }, "_update_policy": { "total": 1461.6193473089945, "count": 1395, "self": 870.7544198080006, "children": { "TorchPPOOptimizer.update": { "total": 590.8649275009939, "count": 68352, "self": 590.8649275009939 } } } } } } }, "trainer_threads": { "total": 1.184000211651437e-06, "count": 1, "self": 1.184000211651437e-06 }, "TrainerController._save_models": { "total": 0.10237390500151378, "count": 1, "self": 0.0019402680027269525, "children": { "RLTrainer._checkpoint": { "total": 0.10043363699878682, "count": 1, "self": 0.10043363699878682 } } } } } } }