{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8386691808700562, "min": 0.672394335269928, "max": 1.6090904474258423, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 2227.50537109375, "min": 1567.004638671875, "max": 6590.83447265625, "count": 100 }, "Pyramids.Step.mean": { "value": 299985.0, "min": 2944.0, "max": 299985.0, "count": 100 }, "Pyramids.Step.sum": { "value": 299985.0, "min": 2944.0, "max": 299985.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0198122076690197, "min": -0.15639443695545197, "max": 0.04895129054784775, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4953051805496216, "min": -3.597071886062622, "max": 1.2237823009490967, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.048741064965724945, "min": -0.159381702542305, "max": 0.3734317719936371, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.2185266017913818, "min": -3.6657791137695312, "max": 9.531417846679688, "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 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06939222758713488, "min": 0.05129323783330619, "max": 0.08596819670250018, "count": 93 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.06939222758713488, "min": 0.05129323783330619, "max": 0.15416727164833277, "count": 93 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007183108794076058, "min": 0.0001334021358161408, "max": 0.02406926324086574, "count": 93 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.007183108794076058, "min": 0.0001334021358161408, "max": 0.02803544798977479, "count": 93 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5270994910000118e-06, "min": 1.5270994910000118e-06, "max": 0.0002959040013653333, "count": 93 }, "Pyramids.Policy.LearningRate.sum": { "value": 1.5270994910000118e-06, "min": 1.5270994910000118e-06, "max": 0.0004536380487873333, "count": 93 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.100509, "min": 0.100509, "max": 0.1986346666666667, "count": 93 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.100509, "min": 0.100509, "max": 0.3512126666666667, "count": 93 }, "Pyramids.Policy.Beta.mean": { "value": 6.084910000000039e-05, "min": 6.084910000000039e-05, "max": 0.009863603200000001, "count": 93 }, "Pyramids.Policy.Beta.sum": { "value": 6.084910000000039e-05, "min": 6.084910000000039e-05, "max": 0.015126145399999999, "count": 93 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.044944848865270615, "min": 0.0422811433672905, "max": 1.0479909181594849, "count": 93 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.044944848865270615, "min": 0.04323822259902954, "max": 1.0479909181594849, "count": 93 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 933.3333333333334, "min": 283.0, "max": 999.0, "count": 64 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 5600.0, "min": 283.0, "max": 15984.0, "count": 64 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5207600563764572, "min": -1.0000000521540642, "max": 1.717000037431717, "count": 68 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -2.603800281882286, "min": -16.000000834465027, "max": 3.8583998680114746, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5207600563764572, "min": -1.0000000521540642, "max": 1.717000037431717, "count": 68 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -2.603800281882286, "min": -16.000000834465027, "max": 3.8583998680114746, "count": 68 }, "Pyramids.Policy.RndReward.mean": { "value": 0.4332942306995392, "min": 0.2255028709769249, "max": 9.63311800956726, "count": 68 }, "Pyramids.Policy.RndReward.sum": { "value": 2.166471153497696, "min": 0.2255028709769249, "max": 96.33118009567261, "count": 68 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676054733", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1676055353" }, "total": 620.802438787, "count": 1, "self": 0.732544941000242, "children": { "run_training.setup": { "total": 0.1652681749999374, "count": 1, "self": 0.1652681749999374 }, "TrainerController.start_learning": { "total": 619.9046256709998, "count": 1, "self": 0.3725324809797712, "children": { "TrainerController._reset_env": { "total": 7.0516776140000275, "count": 1, "self": 7.0516776140000275 }, "TrainerController.advance": { "total": 612.3837014210199, "count": 18921, "self": 0.38513648003413437, "children": { "env_step": { "total": 394.9876312099814, "count": 18921, "self": 361.6783296569463, "children": { "SubprocessEnvManager._take_step": { "total": 33.08237924302102, "count": 18921, "self": 1.3507869650156863, "children": { "TorchPolicy.evaluate": { "total": 31.731592278005337, "count": 18796, "self": 10.677259100004221, "children": { "TorchPolicy.sample_actions": { "total": 21.054333178001116, "count": 18796, "self": 21.054333178001116 } } } } }, "workers": { "total": 0.2269223100140607, "count": 18921, "self": 0.0, "children": { "worker_root": { "total": 618.5263484090012, "count": 18921, "is_parallel": true, "self": 289.65094372599015, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025638600000092993, "count": 1, "is_parallel": true, "self": 0.0008832359999360051, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016806240000732942, "count": 8, "is_parallel": true, "self": 0.0016806240000732942 } } }, "UnityEnvironment.step": { "total": 0.07237013600001774, "count": 1, "is_parallel": true, "self": 0.0005669140002737549, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004382759998406982, "count": 1, "is_parallel": true, "self": 0.0004382759998406982 }, "communicator.exchange": { "total": 0.06910408499993537, "count": 1, "is_parallel": true, "self": 0.06910408499993537 }, "steps_from_proto": { "total": 0.0022608609999679175, "count": 1, "is_parallel": true, "self": 0.0009180509998714115, "children": { "_process_rank_one_or_two_observation": { "total": 0.001342810000096506, "count": 8, "is_parallel": true, "self": 0.001342810000096506 } } } } } } }, "UnityEnvironment.step": { "total": 328.8754046830111, "count": 18920, "is_parallel": true, "self": 9.010022927006958, "children": { "UnityEnvironment._generate_step_input": { "total": 6.504192668020551, "count": 18920, "is_parallel": true, "self": 6.504192668020551 }, "communicator.exchange": { "total": 284.08910702098365, "count": 18920, "is_parallel": true, "self": 284.08910702098365 }, "steps_from_proto": { "total": 29.27208206699993, "count": 18920, "is_parallel": true, "self": 6.311371723993716, "children": { "_process_rank_one_or_two_observation": { "total": 22.960710343006212, "count": 151360, "is_parallel": true, "self": 22.960710343006212 } } } } } } } } } } }, "trainer_advance": { "total": 217.01093373100434, "count": 18921, "self": 0.5888219080031831, "children": { "process_trajectory": { "total": 47.47117167900251, "count": 18921, "self": 47.47117167900251 }, "_update_policy": { "total": 168.95094014399865, "count": 121, "self": 64.30335902100114, "children": { "TorchPPOOptimizer.update": { "total": 104.64758112299751, "count": 6873, "self": 104.64758112299751 } } } } } } }, "trainer_threads": { "total": 8.910001270123757e-07, "count": 1, "self": 8.910001270123757e-07 }, "TrainerController._save_models": { "total": 0.09671326400007274, "count": 1, "self": 0.0013535360001242225, "children": { "RLTrainer._checkpoint": { "total": 0.09535972799994852, "count": 1, "self": 0.09535972799994852 } } } } } } }