{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6416069269180298, "min": 0.6416069269180298, "max": 1.3969576358795166, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19063.42578125, "min": 19063.42578125, "max": 42378.10546875, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2930808365345001, "min": -0.09962756186723709, "max": 0.2930808365345001, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 76.49409484863281, "min": -24.010242462158203, "max": 76.49409484863281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010942352935671806, "min": -0.007483246736228466, "max": 0.5110543370246887, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.855954170227051, "min": -1.9381608963012695, "max": 121.11988067626953, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06508004052555698, "min": 0.06467382014096136, "max": 0.07147914140787846, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9111205673577977, "min": 0.49306234740735777, "max": 1.0441375306759524, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012495636469031946, "min": 0.0005565254659213828, "max": 0.014493545814074554, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17493891056644725, "min": 0.007791356522899359, "max": 0.18327661314348614, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4377403779285745e-06, "min": 7.4377403779285745e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010412836529100005, "min": 0.00010412836529100005, "max": 0.003256482814505799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024792142857143, "min": 0.1024792142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347090000000002, "min": 1.3886848, "max": 2.442923, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025767350714285726, "min": 0.00025767350714285726, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036074291000000014, "min": 0.0036074291000000014, "max": 0.10857087058, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01664787344634533, "min": 0.01632569544017315, "max": 0.6451934576034546, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2330702394247055, "min": 0.2285597324371338, "max": 4.516354084014893, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 520.2982456140351, "min": 520.2982456140351, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29657.0, "min": 15984.0, "max": 32351.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2989930818820823, "min": -1.0000000521540642, "max": 1.2989930818820823, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 75.34159874916077, "min": -30.38280165940523, "max": 75.34159874916077, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2989930818820823, "min": -1.0000000521540642, "max": 1.2989930818820823, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 75.34159874916077, "min": -30.38280165940523, "max": 75.34159874916077, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09040010555201725, "min": 0.09040010555201725, "max": 14.00957185588777, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.243206122017, "min": 4.713947618642123, "max": 224.15314969420433, "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": "1718998179", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719000238" }, "total": 2058.690427979, "count": 1, "self": 0.47644501300010234, "children": { "run_training.setup": { "total": 0.05121739499986688, "count": 1, "self": 0.05121739499986688 }, "TrainerController.start_learning": { "total": 2058.162765571, "count": 1, "self": 1.3477866989092036, "children": { "TrainerController._reset_env": { "total": 2.6793739619999997, "count": 1, "self": 2.6793739619999997 }, "TrainerController.advance": { "total": 2054.0421800890904, "count": 63284, "self": 1.3670525541533607, "children": { "env_step": { "total": 1429.518980960943, "count": 63284, "self": 1299.1645618209604, "children": { "SubprocessEnvManager._take_step": { "total": 129.54073254297418, "count": 63284, "self": 4.6629021270039175, "children": { "TorchPolicy.evaluate": { "total": 124.87783041597027, "count": 62559, "self": 124.87783041597027 } } }, "workers": { "total": 0.8136865970084273, "count": 63284, "self": 0.0, "children": { "worker_root": { "total": 2053.081305473926, "count": 63284, "is_parallel": true, "self": 874.5613234129053, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021043340000233, "count": 1, "is_parallel": true, "self": 0.000611849999813785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014924840002095152, "count": 8, "is_parallel": true, "self": 0.0014924840002095152 } } }, "UnityEnvironment.step": { "total": 0.0859558189999916, "count": 1, "is_parallel": true, "self": 0.0006707689997256239, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004649950001294201, "count": 1, "is_parallel": true, "self": 0.0004649950001294201 }, "communicator.exchange": { "total": 0.08305873000017527, "count": 1, "is_parallel": true, "self": 0.08305873000017527 }, "steps_from_proto": { "total": 0.001761324999961289, "count": 1, "is_parallel": true, "self": 0.00043667500040101004, "children": { "_process_rank_one_or_two_observation": { "total": 0.001324649999560279, "count": 8, "is_parallel": true, "self": 0.001324649999560279 } } } } } } }, "UnityEnvironment.step": { "total": 1178.5199820610208, "count": 63283, "is_parallel": true, "self": 33.39329863400303, "children": { "UnityEnvironment._generate_step_input": { "total": 23.599181494957065, "count": 63283, "is_parallel": true, "self": 23.599181494957065 }, "communicator.exchange": { "total": 1022.0855688680936, "count": 63283, "is_parallel": true, "self": 1022.0855688680936 }, "steps_from_proto": { "total": 99.4419330639671, "count": 63283, "is_parallel": true, "self": 20.08658147004985, "children": { "_process_rank_one_or_two_observation": { "total": 79.35535159391725, "count": 506264, "is_parallel": true, "self": 79.35535159391725 } } } } } } } } } } }, "trainer_advance": { "total": 623.1561465739942, "count": 63284, "self": 2.4612023560005127, "children": { "process_trajectory": { "total": 128.825312884999, "count": 63284, "self": 128.6322753719985, "children": { "RLTrainer._checkpoint": { "total": 0.19303751300049043, "count": 2, "self": 0.19303751300049043 } } }, "_update_policy": { "total": 491.8696313329947, "count": 445, "self": 290.82331846593456, "children": { "TorchPPOOptimizer.update": { "total": 201.04631286706012, "count": 22818, "self": 201.04631286706012 } } } } } } }, "trainer_threads": { "total": 8.560000424040481e-07, "count": 1, "self": 8.560000424040481e-07 }, "TrainerController._save_models": { "total": 0.09342396500005634, "count": 1, "self": 0.0014223749999473512, "children": { "RLTrainer._checkpoint": { "total": 0.09200159000010899, "count": 1, "self": 0.09200159000010899 } } } } } } }