{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43774229288101196, "min": 0.39570972323417664, "max": 1.4746204614639282, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13097.2490234375, "min": 11972.59375, "max": 44734.0859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29878.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29878.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5488067865371704, "min": -0.09620524197816849, "max": 0.5488067865371704, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.47067260742188, "min": -23.185462951660156, "max": 151.47067260742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010214929468929768, "min": -0.001354093779809773, "max": 0.4120699167251587, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8193204402923584, "min": -0.33446115255355835, "max": 97.66056823730469, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06810491638031428, "min": 0.06604391284162425, "max": 0.07184474682473627, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9534688293244, "min": 0.5029132277731538, "max": 1.0596797475154744, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013484394541322857, "min": 0.00017010529492398157, "max": 0.014809620534097553, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18878152357852, "min": 0.0022113688340117603, "max": 0.20733468747736575, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.343176123735718e-06, "min": 7.343176123735718e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010280446573230004, "min": 0.00010280446573230004, "max": 0.003508247030584399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244769285714288, "min": 0.10244769285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342677000000004, "min": 1.3886848, "max": 2.5694156, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025452451642857157, "min": 0.00025452451642857157, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003563343230000002, "min": 0.003563343230000002, "max": 0.11696461843999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012221605516970158, "min": 0.011024300940334797, "max": 0.3999200165271759, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17110247910022736, "min": 0.1543402075767517, "max": 2.7994401454925537, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 371.15384615384613, "min": 357.48837209302326, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28950.0, "min": 16805.0, "max": 33273.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.550420758979661, "min": -0.999862551689148, "max": 1.5727185876390268, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 119.3823984414339, "min": -31.995601654052734, "max": 135.2537985369563, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.550420758979661, "min": -0.999862551689148, "max": 1.5727185876390268, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 119.3823984414339, "min": -31.995601654052734, "max": 135.2537985369563, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04767533038234846, "min": 0.04402748650572057, "max": 8.103497763328692, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6710004394408315, "min": 3.4003821533506198, "max": 137.75946197658777, "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": "1755833594", "python_version": "3.10.18 (main, Aug 8 2025, 17:07:22) [Clang 20.1.4 ]", "command_line_arguments": "/home/huinker/Coding/python/.venv/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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1755834563" }, "total": 969.1998078129996, "count": 1, "self": 0.3187359979997382, "children": { "run_training.setup": { "total": 0.016594144999999116, "count": 1, "self": 0.016594144999999116 }, "TrainerController.start_learning": { "total": 968.8644776699998, "count": 1, "self": 1.125586232956266, "children": { "TrainerController._reset_env": { "total": 1.6382078729998284, "count": 1, "self": 1.6382078729998284 }, "TrainerController.advance": { "total": 966.0495865510438, "count": 63531, "self": 1.208171482085163, "children": { "env_step": { "total": 632.4431767699612, "count": 63531, "self": 537.6827582959513, "children": { "SubprocessEnvManager._take_step": { "total": 93.94131741699448, "count": 63531, "self": 2.8692294469506123, "children": { "TorchPolicy.evaluate": { "total": 91.07208797004387, "count": 62546, "self": 91.07208797004387 } } }, "workers": { "total": 0.8191010570153594, "count": 63531, "self": 0.0, "children": { "worker_root": { "total": 967.3874754300491, "count": 63531, "is_parallel": true, "self": 495.36792228305876, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0011326329999974405, "count": 1, "is_parallel": true, "self": 0.00033361600026182714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007990169997356134, "count": 8, "is_parallel": true, "self": 0.0007990169997356134 } } }, "UnityEnvironment.step": { "total": 0.027734078999856138, "count": 1, "is_parallel": true, "self": 0.0001875850002761581, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002896879996114876, "count": 1, "is_parallel": true, "self": 0.0002896879996114876 }, "communicator.exchange": { "total": 0.026620441999966715, "count": 1, "is_parallel": true, "self": 0.026620441999966715 }, "steps_from_proto": { "total": 0.0006363640000017767, "count": 1, "is_parallel": true, "self": 0.00014484499934042105, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004915190006613557, "count": 8, "is_parallel": true, "self": 0.0004915190006613557 } } } } } } }, "UnityEnvironment.step": { "total": 472.01955314699035, "count": 63530, "is_parallel": true, "self": 13.861760873021467, "children": { "UnityEnvironment._generate_step_input": { "total": 10.748551432009663, "count": 63530, "is_parallel": true, "self": 10.748551432009663 }, "communicator.exchange": { "total": 407.92792290604984, "count": 63530, "is_parallel": true, "self": 407.92792290604984 }, "steps_from_proto": { "total": 39.481317935909374, "count": 63530, "is_parallel": true, "self": 9.491694915897824, "children": { "_process_rank_one_or_two_observation": { "total": 29.98962302001155, "count": 508240, "is_parallel": true, "self": 29.98962302001155 } } } } } } } } } } }, "trainer_advance": { "total": 332.3982382989975, "count": 63531, "self": 2.3511682590456076, "children": { "process_trajectory": { "total": 69.47510156794851, "count": 63531, "self": 69.37203262894809, "children": { "RLTrainer._checkpoint": { "total": 0.10306893900042269, "count": 2, "self": 0.10306893900042269 } } }, "_update_policy": { "total": 260.5719684720034, "count": 451, "self": 144.43064454199475, "children": { "TorchPPOOptimizer.update": { "total": 116.14132393000864, "count": 22821, "self": 116.14132393000864 } } } } } } }, "trainer_threads": { "total": 2.373999905103119e-06, "count": 1, "self": 2.373999905103119e-06 }, "TrainerController._save_models": { "total": 0.051094638999984454, "count": 1, "self": 0.0010993959999723302, "children": { "RLTrainer._checkpoint": { "total": 0.049995243000012124, "count": 1, "self": 0.049995243000012124 } } } } } } }