{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5475189685821533, "min": 0.5475189685821533, "max": 1.4914255142211914, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16390.52734375, "min": 16390.52734375, "max": 45243.8828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.020159991458058357, "min": -0.23467543721199036, "max": 0.07543991506099701, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 4.919037818908691, "min": -55.618080139160156, "max": 18.55821990966797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005924496334046125, "min": 0.0024194782599806786, "max": 0.2376379370689392, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.4455771446228027, "min": 0.5951916575431824, "max": 56.3201904296875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06689702364309894, "min": 0.0661180169186757, "max": 0.07442422055057299, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9365583310033851, "min": 0.49472916313954196, "max": 1.0906003132940716, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.004978707440665605, "min": 6.593483457572038e-05, "max": 0.007965621430273693, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06970190416931847, "min": 0.0009230876840600852, "max": 0.1115187000238317, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.654168877214282e-06, "min": 7.654168877214282e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010715836428099994, "min": 0.00010715836428099994, "max": 0.0031374437541855003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255135714285717, "min": 0.10255135714285717, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357190000000004, "min": 1.3691136000000002, "max": 2.3598708999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026488057857142845, "min": 0.00026488057857142845, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003708328099999998, "min": 0.003708328099999998, "max": 0.10460686854999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01039099134504795, "min": 0.01039099134504795, "max": 0.24918627738952637, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1454738825559616, "min": 0.1454738825559616, "max": 1.7443039417266846, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 869.1388888888889, "min": 790.2972972972973, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31289.0, "min": 15984.0, "max": 32072.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.25844449260168606, "min": -1.0000000521540642, "max": 0.23642698111566338, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -9.304001733660698, "min": -32.000001668930054, "max": 8.747798301279545, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.25844449260168606, "min": -1.0000000521540642, "max": 0.23642698111566338, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -9.304001733660698, "min": -32.000001668930054, "max": 8.747798301279545, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09401227333970989, "min": 0.09029115588605605, "max": 4.947000477928668, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.384441840229556, "min": 3.175957511004526, "max": 79.15200764685869, "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": "1785844272", "python_version": "3.10.12 (main, Jun 22 2026, 18:55:27) [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 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": "1785845805" }, "total": 1533.152407906, "count": 1, "self": 0.3728411939991929, "children": { "run_training.setup": { "total": 0.02337632299895631, "count": 1, "self": 0.02337632299895631 }, "TrainerController.start_learning": { "total": 1532.7561903890019, "count": 1, "self": 0.8733584822548437, "children": { "TrainerController._reset_env": { "total": 1.655437023997365, "count": 1, "self": 1.655437023997365 }, "TrainerController.advance": { "total": 1530.18091391075, "count": 63240, "self": 0.8800646507406782, "children": { "env_step": { "total": 1048.600765421801, "count": 63240, "self": 965.7343789121915, "children": { "SubprocessEnvManager._take_step": { "total": 82.31308745218848, "count": 63240, "self": 3.7599787513827323, "children": { "TorchPolicy.evaluate": { "total": 78.55310870080575, "count": 62568, "self": 78.55310870080575 } } }, "workers": { "total": 0.5532990574210999, "count": 63240, "self": 0.0, "children": { "worker_root": { "total": 1530.0318913452356, "count": 63240, "is_parallel": true, "self": 642.297162576815, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004580871001962805, "count": 1, "is_parallel": true, "self": 0.0015508070100622717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0030300639919005334, "count": 8, "is_parallel": true, "self": 0.0030300639919005334 } } }, "UnityEnvironment.step": { "total": 0.041431330999330385, "count": 1, "is_parallel": true, "self": 0.0004844369977945462, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005691539990948513, "count": 1, "is_parallel": true, "self": 0.0005691539990948513 }, "communicator.exchange": { "total": 0.038835522002045764, "count": 1, "is_parallel": true, "self": 0.038835522002045764 }, "steps_from_proto": { "total": 0.0015422180003952235, "count": 1, "is_parallel": true, "self": 0.00031709200266050175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012251259977347218, "count": 8, "is_parallel": true, "self": 0.0012251259977347218 } } } } } } }, "UnityEnvironment.step": { "total": 887.7347287684206, "count": 63239, "is_parallel": true, "self": 24.191604329997062, "children": { "UnityEnvironment._generate_step_input": { "total": 16.889520471100695, "count": 63239, "is_parallel": true, "self": 16.889520471100695 }, "communicator.exchange": { "total": 777.8425504876541, "count": 63239, "is_parallel": true, "self": 777.8425504876541 }, "steps_from_proto": { "total": 68.81105347966877, "count": 63239, "is_parallel": true, "self": 14.5228054366562, "children": { "_process_rank_one_or_two_observation": { "total": 54.28824804301257, "count": 505912, "is_parallel": true, "self": 54.28824804301257 } } } } } } } } } } }, "trainer_advance": { "total": 480.70008383820823, "count": 63240, "self": 1.6479720214483677, "children": { "process_trajectory": { "total": 80.66991492874513, "count": 63240, "self": 80.52745297674483, "children": { "RLTrainer._checkpoint": { "total": 0.14246195200030343, "count": 2, "self": 0.14246195200030343 } } }, "_update_policy": { "total": 398.38219688801473, "count": 431, "self": 201.8261388165738, "children": { "TorchPPOOptimizer.update": { "total": 196.55605807144093, "count": 22800, "self": 196.55605807144093 } } } } } } }, "trainer_threads": { "total": 1.1109987099189311e-06, "count": 1, "self": 1.1109987099189311e-06 }, "TrainerController._save_models": { "total": 0.04647986100098933, "count": 1, "self": 0.0015984290002961643, "children": { "RLTrainer._checkpoint": { "total": 0.04488143200069317, "count": 1, "self": 0.04488143200069317 } } } } } } }