{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3344995677471161, "min": 0.3344995677471161, "max": 1.4375325441360474, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10281.1787109375, "min": 10281.1787109375, "max": 43608.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989968.0, "min": 29952.0, "max": 989968.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5158936977386475, "min": -0.10864276438951492, "max": 0.5748215317726135, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 139.80718994140625, "min": -26.182907104492188, "max": 158.65074157714844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01452154852449894, "min": -0.016901008784770966, "max": 0.5650400519371033, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.9353396892547607, "min": -4.647777557373047, "max": 133.91448974609375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06804376509464026, "min": 0.06545092842231194, "max": 0.07332693469989358, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9526127113249637, "min": 0.5132885428992551, "max": 1.0489613994529159, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012367357769372861, "min": 0.00012239541067588894, "max": 0.015524638260765906, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17314300877122005, "min": 0.001591140338786556, "max": 0.2173449356507227, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.427176095735712e-06, "min": 7.427176095735712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010398046534029996, "min": 0.00010398046534029996, "max": 0.0031391405536199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247569285714288, "min": 0.10247569285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346597000000003, "min": 1.3886848, "max": 2.3588626, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002573217164285714, "min": 0.0002573217164285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036025040299999993, "min": 0.0036025040299999993, "max": 0.10466337199, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.018506214022636414, "min": 0.018334995955228806, "max": 0.6839659810066223, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2590869963169098, "min": 0.2566899359226227, "max": 4.787761688232422, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.6875, "min": 354.6875, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28375.0, "min": 15984.0, "max": 32843.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5452674843370915, "min": -1.0000000521540642, "max": 1.625868401048999, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.62139874696732, "min": -31.999601677060127, "max": 136.44819815456867, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5452674843370915, "min": -1.0000000521540642, "max": 1.625868401048999, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.62139874696732, "min": -31.999601677060127, "max": 136.44819815456867, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06690401317428041, "min": 0.06690401317428041, "max": 14.13746533356607, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.352321053942433, "min": 5.352321053942433, "max": 226.1994453370571, "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": "1782548233", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [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 --force", "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": "1782550633" }, "total": 2399.547294791, "count": 1, "self": 0.484860483999455, "children": { "run_training.setup": { "total": 0.02262999000004129, "count": 1, "self": 0.02262999000004129 }, "TrainerController.start_learning": { "total": 2399.0398043170003, "count": 1, "self": 1.5288609009598986, "children": { "TrainerController._reset_env": { "total": 3.017581760999974, "count": 1, "self": 3.017581760999974 }, "TrainerController.advance": { "total": 2394.4107916130406, "count": 63707, "self": 1.6104051970473847, "children": { "env_step": { "total": 1753.6581716989922, "count": 63707, "self": 1592.1897906100553, "children": { "SubprocessEnvManager._take_step": { "total": 160.52382788296802, "count": 63707, "self": 4.94151717894681, "children": { "TorchPolicy.evaluate": { "total": 155.5823107040212, "count": 62556, "self": 155.5823107040212 } } }, "workers": { "total": 0.9445532059689867, "count": 63707, "self": 0.0, "children": { "worker_root": { "total": 2393.6816016930084, "count": 63707, "is_parallel": true, "self": 925.9654611600181, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004386593000049288, "count": 1, "is_parallel": true, "self": 0.0030343820000098276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013522110000394605, "count": 8, "is_parallel": true, "self": 0.0013522110000394605 } } }, "UnityEnvironment.step": { "total": 0.052129808000017874, "count": 1, "is_parallel": true, "self": 0.0005613690000245697, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004760289999694578, "count": 1, "is_parallel": true, "self": 0.0004760289999694578 }, "communicator.exchange": { "total": 0.04929688599997917, "count": 1, "is_parallel": true, "self": 0.04929688599997917 }, "steps_from_proto": { "total": 0.0017955240000446793, "count": 1, "is_parallel": true, "self": 0.0004065470001251015, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013889769999195778, "count": 8, "is_parallel": true, "self": 0.0013889769999195778 } } } } } } }, "UnityEnvironment.step": { "total": 1467.7161405329903, "count": 63706, "is_parallel": true, "self": 35.351216416972875, "children": { "UnityEnvironment._generate_step_input": { "total": 24.545753086047284, "count": 63706, "is_parallel": true, "self": 24.545753086047284 }, "communicator.exchange": { "total": 1291.5603934100095, "count": 63706, "is_parallel": true, "self": 1291.5603934100095 }, "steps_from_proto": { "total": 116.25877761996082, "count": 63706, "is_parallel": true, "self": 24.216493389776588, "children": { "_process_rank_one_or_two_observation": { "total": 92.04228423018424, "count": 509648, "is_parallel": true, "self": 92.04228423018424 } } } } } } } } } } }, "trainer_advance": { "total": 639.1422147170009, "count": 63707, "self": 2.805766320010548, "children": { "process_trajectory": { "total": 112.64022372798797, "count": 63707, "self": 112.41329223398782, "children": { "RLTrainer._checkpoint": { "total": 0.226931494000155, "count": 2, "self": 0.226931494000155 } } }, "_update_policy": { "total": 523.6962246690024, "count": 438, "self": 280.41078707702536, "children": { "TorchPPOOptimizer.update": { "total": 243.28543759197703, "count": 22845, "self": 243.28543759197703 } } } } } } }, "trainer_threads": { "total": 7.570001798740122e-07, "count": 1, "self": 7.570001798740122e-07 }, "TrainerController._save_models": { "total": 0.08256928499986316, "count": 1, "self": 0.001115804000164644, "children": { "RLTrainer._checkpoint": { "total": 0.08145348099969851, "count": 1, "self": 0.08145348099969851 } } } } } } }