{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.1095993518829346, "min": 1.1095993518829346, "max": 1.5281413793563843, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 33234.71875, "min": 33234.71875, "max": 46357.6953125, "count": 3 }, "Pyramids.Step.mean": { "value": 89964.0, "min": 29952.0, "max": 89964.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89964.0, "min": 29952.0, "max": 89964.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.1073603630065918, "min": -0.2275964617729187, "max": -0.1073603630065918, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -25.87384796142578, "min": -53.94036102294922, "max": -25.87384796142578, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.13780467212200165, "min": 0.1295059472322464, "max": 0.18704542517662048, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.2109260559082, "min": 30.692909240722656, "max": 44.89090347290039, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06716353461042082, "min": 0.06716353461042082, "max": 0.07175296464250025, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6716353461042083, "min": 0.4735668081580795, "max": 0.6716353461042083, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001088611935647835, "min": 0.001025184603455058, "max": 0.004784235185225745, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.01088611935647835, "min": 0.007176292224185405, "max": 0.03348964629658022, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.57332747556e-05, "min": 7.57332747556e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000757332747556, "min": 0.000757332747556, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1252444, "min": 0.1252444, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.2524440000000001, "min": 1.0911359999999999, "max": 1.2868480000000002, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025319155600000004, "min": 0.0025319155600000004, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.025319155600000004, "min": 0.025319155600000004, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.09883655607700348, "min": 0.09883655607700348, "max": 0.3050103187561035, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.9883655905723572, "min": 0.9883655905723572, "max": 2.1350722312927246, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 979.7272727272727, "min": 979.7272727272727, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32331.0, "min": 15984.0, "max": 32331.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.920078838639187, "min": -1.0000000521540642, "max": -0.920078838639187, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -30.362601675093174, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.920078838639187, "min": -1.0000000521540642, "max": -0.920078838639187, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -30.362601675093174, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.1134050547173528, "min": 1.1134050547173528, "max": 5.731844781897962, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 36.742366805672646, "min": 36.742366805672646, "max": 91.7095165103674, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756505186", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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 Training3 --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": "1756505379" }, "total": 192.61450050700023, "count": 1, "self": 0.6423556210002062, "children": { "run_training.setup": { "total": 0.020055898999999044, "count": 1, "self": 0.020055898999999044 }, "TrainerController.start_learning": { "total": 191.95208898700002, "count": 1, "self": 0.12651569198669677, "children": { "TrainerController._reset_env": { "total": 2.976642689000073, "count": 1, "self": 2.976642689000073 }, "TrainerController.advance": { "total": 188.68799452601297, "count": 6263, "self": 0.1372446490099719, "children": { "env_step": { "total": 123.1972438070211, "count": 6263, "self": 108.04269595208143, "children": { "SubprocessEnvManager._take_step": { "total": 15.075828517978607, "count": 6263, "self": 0.4565189839731829, "children": { "TorchPolicy.evaluate": { "total": 14.619309534005424, "count": 6260, "self": 14.619309534005424 } } }, "workers": { "total": 0.0787193369610577, "count": 6263, "self": 0.0, "children": { "worker_root": { "total": 191.42191162200243, "count": 6263, "is_parallel": true, "self": 93.97238270498065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026602499997352425, "count": 1, "is_parallel": true, "self": 0.0007371289993898245, "children": { "_process_rank_one_or_two_observation": { "total": 0.001923121000345418, "count": 8, "is_parallel": true, "self": 0.001923121000345418 } } }, "UnityEnvironment.step": { "total": 0.04725945199970738, "count": 1, "is_parallel": true, "self": 0.0006158769992907764, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047801900018384913, "count": 1, "is_parallel": true, "self": 0.00047801900018384913 }, "communicator.exchange": { "total": 0.044459821000145894, "count": 1, "is_parallel": true, "self": 0.044459821000145894 }, "steps_from_proto": { "total": 0.001705735000086861, "count": 1, "is_parallel": true, "self": 0.00040631000001667417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012994250000701868, "count": 8, "is_parallel": true, "self": 0.0012994250000701868 } } } } } } }, "UnityEnvironment.step": { "total": 97.44952891702178, "count": 6262, "is_parallel": true, "self": 3.1937775220312687, "children": { "UnityEnvironment._generate_step_input": { "total": 2.2604773489720174, "count": 6262, "is_parallel": true, "self": 2.2604773489720174 }, "communicator.exchange": { "total": 82.57713548500942, "count": 6262, "is_parallel": true, "self": 82.57713548500942 }, "steps_from_proto": { "total": 9.418138561009073, "count": 6262, "is_parallel": true, "self": 1.856509808039391, "children": { "_process_rank_one_or_two_observation": { "total": 7.561628752969682, "count": 50096, "is_parallel": true, "self": 7.561628752969682 } } } } } } } } } } }, "trainer_advance": { "total": 65.3535060699819, "count": 6263, "self": 0.1674284539767541, "children": { "process_trajectory": { "total": 11.78368719300397, "count": 6263, "self": 11.78368719300397 }, "_update_policy": { "total": 53.40239042300118, "count": 27, "self": 29.672020923001583, "children": { "TorchPPOOptimizer.update": { "total": 23.730369499999597, "count": 2286, "self": 23.730369499999597 } } } } } } }, "trainer_threads": { "total": 1.1969996194238774e-06, "count": 1, "self": 1.1969996194238774e-06 }, "TrainerController._save_models": { "total": 0.16093488300066383, "count": 1, "self": 0.00164775500070391, "children": { "RLTrainer._checkpoint": { "total": 0.15928712799995992, "count": 1, "self": 0.15928712799995992 } } } } } } }