{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0541887283325195, "min": 1.0541887283325195, "max": 1.6094080209732056, "count": 25 }, "Pyramids.Policy.Entropy.sum": { "value": 2158.978515625, "min": 1833.224609375, "max": 3296.067626953125, "count": 25 }, "Pyramids.Step.mean": { "value": 49988.0, "min": 1984.0, "max": 49988.0, "count": 25 }, "Pyramids.Step.sum": { "value": 49988.0, "min": 1984.0, "max": 49988.0, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05214060842990875, "min": -0.0790453627705574, "max": 0.06703026592731476, "count": 25 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -1.66849946975708, "min": -2.6922693252563477, "max": 2.0779383182525635, "count": 25 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 9.569377899169922, "min": -0.018739579245448112, "max": 10.16330337524414, "count": 25 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 306.2200927734375, "min": -0.5809269547462463, "max": 368.16986083984375, "count": 25 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.04542937591947891, "min": 0.04542937591947891, "max": 0.05563530861400068, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.04542937591947891, "min": 0.04542937591947891, "max": 0.05563530861400068, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.21214669170203032, "min": 0.21214669170203032, "max": 8.107888515790304, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21214669170203032, "min": 0.21214669170203032, "max": 8.107888515790304, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.216097927999988e-06, "min": 6.216097927999988e-06, "max": 0.00026928001024, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 6.216097927999988e-06, "min": 6.216097927999988e-06, "max": 0.00026928001024, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10207199999999995, "min": 0.10207199999999995, "max": 0.18975999999999998, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.10207199999999995, "min": 0.10207199999999995, "max": 0.18975999999999998, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011339279999999979, "min": 0.00011339279999999979, "max": 0.004489024, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.00011339279999999979, "min": 0.00011339279999999979, "max": 0.004489024, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.35717928409576416, "min": 0.35717928409576416, "max": 1.3651211261749268, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.35717928409576416, "min": 0.35717928409576416, "max": 1.3651211261749268, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 619.0, "max": 999.0, "count": 4 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 14985.0, "min": 619.0, "max": 15984.0, "count": 4 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": 1.3809999898076057, "count": 6 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -15.000000670552254, "min": -15.000000670552254, "max": 1.3809999898076057, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": 1.3809999898076057, "count": 6 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -15.000000670552254, "min": -15.000000670552254, "max": 1.3809999898076057, "count": 6 }, "Pyramids.Policy.RndReward.mean": { "value": 84.27403333981832, "min": 66.98070955276489, "max": 272.6755060036977, "count": 6 }, "Pyramids.Policy.RndReward.sum": { "value": 1264.1105000972748, "min": 66.98070955276489, "max": 4090.1325900554657, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1773035737", "python_version": "3.10.12 (main, Jan 26 2026, 14:55:28) [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=PyramidsTraining6 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1773035841" }, "total": 103.66781204400013, "count": 1, "self": 0.488246768999943, "children": { "run_training.setup": { "total": 0.022889024000050995, "count": 1, "self": 0.022889024000050995 }, "TrainerController.start_learning": { "total": 103.15667625100014, "count": 1, "self": 0.06532942600051683, "children": { "TrainerController._reset_env": { "total": 2.2636635339999884, "count": 1, "self": 2.2636635339999884 }, "TrainerController.advance": { "total": 100.6935545199999, "count": 3133, "self": 0.06744813999466714, "children": { "env_step": { "total": 66.201567256006, "count": 3133, "self": 56.73546267200254, "children": { "SubprocessEnvManager._take_step": { "total": 9.42420150599537, "count": 3133, "self": 0.2330886769996141, "children": { "TorchPolicy.evaluate": { "total": 9.191112828995756, "count": 3132, "self": 9.191112828995756 } } }, "workers": { "total": 0.04190307800809023, "count": 3133, "self": 0.0, "children": { "worker_root": { "total": 102.5950059210063, "count": 3133, "is_parallel": true, "self": 51.59358566801939, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017876499996418715, "count": 1, "is_parallel": true, "self": 0.0005678990000888007, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012197509995530709, "count": 8, "is_parallel": true, "self": 0.0012197509995530709 } } }, "UnityEnvironment.step": { "total": 0.04999150599996938, "count": 1, "is_parallel": true, "self": 0.0005314650002219423, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004603439997481473, "count": 1, "is_parallel": true, "self": 0.0004603439997481473 }, "communicator.exchange": { "total": 0.04718070399985663, "count": 1, "is_parallel": true, "self": 0.04718070399985663 }, "steps_from_proto": { "total": 0.0018189930001426546, "count": 1, "is_parallel": true, "self": 0.0005027259999224043, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013162670002202503, "count": 8, "is_parallel": true, "self": 0.0013162670002202503 } } } } } } }, "UnityEnvironment.step": { "total": 51.00142025298692, "count": 3132, "is_parallel": true, "self": 1.631293846997778, "children": { "UnityEnvironment._generate_step_input": { "total": 1.1118156179863945, "count": 3132, "is_parallel": true, "self": 1.1118156179863945 }, "communicator.exchange": { "total": 42.98308750000797, "count": 3132, "is_parallel": true, "self": 42.98308750000797 }, "steps_from_proto": { "total": 5.275223287994777, "count": 3132, "is_parallel": true, "self": 1.1024208249386902, "children": { "_process_rank_one_or_two_observation": { "total": 4.172802463056087, "count": 25056, "is_parallel": true, "self": 4.172802463056087 } } } } } } } } } } }, "trainer_advance": { "total": 34.42453912399924, "count": 3133, "self": 0.08457219098136193, "children": { "process_trajectory": { "total": 13.634503882018635, "count": 3133, "self": 10.160530354019102, "children": { "RLTrainer._checkpoint": { "total": 3.473973527999533, "count": 25, "self": 3.473973527999533 } } }, "_update_policy": { "total": 20.705463050999242, "count": 10, "self": 12.852384412005904, "children": { "TorchPPOOptimizer.update": { "total": 7.853078638993338, "count": 570, "self": 7.853078638993338 } } } } } } }, "trainer_threads": { "total": 8.769998203206342e-07, "count": 1, "self": 8.769998203206342e-07 }, "TrainerController._save_models": { "total": 0.13412789399990288, "count": 1, "self": 0.0040049859999271575, "children": { "RLTrainer._checkpoint": { "total": 0.13012290799997572, "count": 1, "self": 0.13012290799997572 } } } } } } }