{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13678209483623505, "min": 0.13504451513290405, "max": 1.3998075723648071, "count": 84 }, "Pyramids.Policy.Entropy.sum": { "value": 4081.57763671875, "min": 4029.728271484375, "max": 42464.5625, "count": 84 }, "Pyramids.Step.mean": { "value": 2519933.0, "min": 29952.0, "max": 2519933.0, "count": 84 }, "Pyramids.Step.sum": { "value": 2519933.0, "min": 29952.0, "max": 2519933.0, "count": 84 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7510318756103516, "min": -0.1373794972896576, "max": 0.7866915464401245, "count": 84 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 217.7992401123047, "min": -33.10845947265625, "max": 234.43408203125, "count": 84 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.005109967198222876, "min": -0.039171863347291946, "max": 0.33357614278793335, "count": 84 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.4818904399871826, "min": -11.399012565612793, "max": 79.05754852294922, "count": 84 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07143887223459648, "min": 0.06491286997953676, "max": 0.07301841387434709, "count": 84 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0001442112843508, "min": 0.5084852611896282, "max": 1.069757589871776, "count": 84 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016042223005483504, "min": 0.0004185282670684428, "max": 0.018457594326242714, "count": 84 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22459112207676904, "min": 0.004603810937752871, "max": 0.25873768631900734, "count": 84 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.947723350761666e-05, "min": 4.947723350761666e-05, "max": 0.00029838354339596195, "count": 84 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0006926812691066332, "min": 0.0006926812691066332, "max": 0.0039276906907698, "count": 84 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.11649238333333334, "min": 0.11649238333333334, "max": 0.19946118095238097, "count": 84 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.6308933666666667, "min": 1.3962282666666668, "max": 2.7524872999999994, "count": 84 }, "Pyramids.Policy.Beta.mean": { "value": 0.0016575890950000004, "min": 0.0016575890950000004, "max": 0.009946171977142856, "count": 84 }, "Pyramids.Policy.Beta.sum": { "value": 0.023206247330000006, "min": 0.023206247330000006, "max": 0.13093209698, "count": 84 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0051178717985749245, "min": 0.004900889005511999, "max": 0.38831979036331177, "count": 84 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07165020704269409, "min": 0.06861244887113571, "max": 2.718238592147827, "count": 84 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 239.73275862068965, "min": 239.1153846153846, "max": 999.0, "count": 84 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27809.0, "min": 15984.0, "max": 33421.0, "count": 84 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7257672292662078, "min": -1.0000000521540642, "max": 1.7503852323919047, "count": 84 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 200.1889985948801, "min": -31.998801678419113, "max": 226.91479770839214, "count": 84 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7257672292662078, "min": -1.0000000521540642, "max": 1.7503852323919047, "count": 84 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 200.1889985948801, "min": -31.998801678419113, "max": 226.91479770839214, "count": 84 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012797177567022274, "min": 0.01255143990923758, "max": 7.680468650534749, "count": 84 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4844725977745838, "min": 1.4844725977745838, "max": 122.88749840855598, "count": 84 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 84 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 84 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1758660578", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1758666308" }, "total": 5729.793542461, "count": 1, "self": 0.365242269999726, "children": { "run_training.setup": { "total": 0.0272840970001198, "count": 1, "self": 0.0272840970001198 }, "TrainerController.start_learning": { "total": 5729.401016094, "count": 1, "self": 2.9606857680846588, "children": { "TrainerController._reset_env": { "total": 2.0006278279997787, "count": 1, "self": 2.0006278279997787 }, "TrainerController.advance": { "total": 5724.316169030915, "count": 164016, "self": 3.143203390705821, "children": { "env_step": { "total": 4116.540633953187, "count": 164016, "self": 3774.6020308954753, "children": { "SubprocessEnvManager._take_step": { "total": 340.0922972338194, "count": 164016, "self": 10.75231426284563, "children": { "TorchPolicy.evaluate": { "total": 329.3399829709738, "count": 158334, "self": 329.3399829709738 } } }, "workers": { "total": 1.846305823892635, "count": 164015, "self": 0.0, "children": { "worker_root": { "total": 5712.530110626989, "count": 164015, "is_parallel": true, "self": 2214.321897953169, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018071310000777885, "count": 1, "is_parallel": true, "self": 0.0006049250005162321, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012022059995615564, "count": 8, "is_parallel": true, "self": 0.0012022059995615564 } } }, "UnityEnvironment.step": { "total": 0.047349702999781584, "count": 1, "is_parallel": true, "self": 0.0005165189995750552, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005104580000079295, "count": 1, "is_parallel": true, "self": 0.0005104580000079295 }, "communicator.exchange": { "total": 0.04463051299990184, "count": 1, "is_parallel": true, "self": 0.04463051299990184 }, "steps_from_proto": { "total": 0.0016922130002967606, "count": 1, "is_parallel": true, "self": 0.00036018399987369776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013320290004230628, "count": 8, "is_parallel": true, "self": 0.0013320290004230628 } } } } } } }, "UnityEnvironment.step": { "total": 3498.20821267382, "count": 164014, "is_parallel": true, "self": 81.13729878470986, "children": { "UnityEnvironment._generate_step_input": { "total": 55.77460816291796, "count": 164014, "is_parallel": true, "self": 55.77460816291796 }, "communicator.exchange": { "total": 3105.268138607021, "count": 164014, "is_parallel": true, "self": 3105.268138607021 }, "steps_from_proto": { "total": 256.0281671191715, "count": 164014, "is_parallel": true, "self": 52.24613533764523, "children": { "_process_rank_one_or_two_observation": { "total": 203.78203178152626, "count": 1312112, "is_parallel": true, "self": 203.78203178152626 } } } } } } } } } } }, "trainer_advance": { "total": 1604.6323316870225, "count": 164015, "self": 5.948622434982099, "children": { "process_trajectory": { "total": 310.0110562190316, "count": 164015, "self": 309.61282362603197, "children": { "RLTrainer._checkpoint": { "total": 0.39823259299964775, "count": 5, "self": 0.39823259299964775 } } }, "_update_policy": { "total": 1288.6726530330088, "count": 1174, "self": 720.9800121889562, "children": { "TorchPPOOptimizer.update": { "total": 567.6926408440527, "count": 57777, "self": 567.6926408440527 } } } } } } }, "trainer_threads": { "total": 1.3230001059127972e-06, "count": 1, "self": 1.3230001059127972e-06 }, "TrainerController._save_models": { "total": 0.12353214399990975, "count": 1, "self": 0.0015186809996521333, "children": { "RLTrainer._checkpoint": { "total": 0.12201346300025762, "count": 1, "self": 0.12201346300025762 } } } } } } }