{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6217910647392273, "min": 0.6217910647392273, "max": 1.3986022472381592, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18693.52734375, "min": 18693.52734375, "max": 42427.99609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.33308297395706177, "min": -0.11171487718820572, "max": 0.3903945982456207, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.26773834228516, "min": -26.81157112121582, "max": 102.28338623046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.026259221136569977, "min": -0.007511988282203674, "max": 0.4488699436187744, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.879915714263916, "min": -1.9080450534820557, "max": 106.3821792602539, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07076957303104878, "min": 0.06499893968058233, "max": 0.07492170639918852, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9907740224346828, "min": 0.5030805370382343, "max": 1.0225232154286157, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010361524677093604, "min": 0.00019326318392288037, "max": 0.012174115216667492, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14506134547931046, "min": 0.0019326318392288036, "max": 0.1704376130333449, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.50785464027143e-06, "min": 7.50785464027143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010510996496380003, "min": 0.00010510996496380003, "max": 0.0030198908933698, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250258571428572, "min": 0.10250258571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350362, "min": 1.3691136000000002, "max": 2.3584612000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600083128571429, "min": 0.0002600083128571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036401163800000007, "min": 0.0036401163800000007, "max": 0.10069235697999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009019111283123493, "min": 0.008629250340163708, "max": 0.5635762214660645, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12626755237579346, "min": 0.12080950289964676, "max": 3.945033550262451, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 511.8, "min": 485.2295081967213, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30708.0, "min": 15984.0, "max": 32599.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1805796308790224, "min": -1.0000000521540642, "max": 1.2851966941942934, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 69.65419822186232, "min": -32.000001668930054, "max": 78.3969983458519, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1805796308790224, "min": -1.0000000521540642, "max": 1.2851966941942934, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 69.65419822186232, "min": -32.000001668930054, "max": 78.3969983458519, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.047923821161729996, "min": 0.04551308719413195, "max": 10.685377827845514, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8275054485420696, "min": 2.6397590572596528, "max": 170.96604524552822, "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": "1747957016", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [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 --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747959078" }, "total": 2062.388096179, "count": 1, "self": 0.648155021000548, "children": { "run_training.setup": { "total": 0.018212105999737105, "count": 1, "self": 0.018212105999737105 }, "TrainerController.start_learning": { "total": 2061.721729052, "count": 1, "self": 1.2392506339456304, "children": { "TrainerController._reset_env": { "total": 2.854934856, "count": 1, "self": 2.854934856 }, "TrainerController.advance": { "total": 2057.5476565050544, "count": 63446, "self": 1.2557198249755857, "children": { "env_step": { "total": 1390.047780130074, "count": 63446, "self": 1242.5126550110526, "children": { "SubprocessEnvManager._take_step": { "total": 146.79199862501355, "count": 63446, "self": 4.454809547062723, "children": { "TorchPolicy.evaluate": { "total": 142.33718907795082, "count": 62562, "self": 142.33718907795082 } } }, "workers": { "total": 0.7431264940078108, "count": 63446, "self": 0.0, "children": { "worker_root": { "total": 2057.2026753729388, "count": 63446, "is_parallel": true, "self": 918.3083111049459, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020880949996353593, "count": 1, "is_parallel": true, "self": 0.0006878979993416579, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014001970002937014, "count": 8, "is_parallel": true, "self": 0.0014001970002937014 } } }, "UnityEnvironment.step": { "total": 0.06930246199999601, "count": 1, "is_parallel": true, "self": 0.0005931760001658404, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004495159996622533, "count": 1, "is_parallel": true, "self": 0.0004495159996622533 }, "communicator.exchange": { "total": 0.06662056799996208, "count": 1, "is_parallel": true, "self": 0.06662056799996208 }, "steps_from_proto": { "total": 0.0016392020002058416, "count": 1, "is_parallel": true, "self": 0.00034346900019954774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012957330000062939, "count": 8, "is_parallel": true, "self": 0.0012957330000062939 } } } } } } }, "UnityEnvironment.step": { "total": 1138.8943642679928, "count": 63445, "is_parallel": true, "self": 30.810982908969436, "children": { "UnityEnvironment._generate_step_input": { "total": 22.615299728051014, "count": 63445, "is_parallel": true, "self": 22.615299728051014 }, "communicator.exchange": { "total": 991.3801436059744, "count": 63445, "is_parallel": true, "self": 991.3801436059744 }, "steps_from_proto": { "total": 94.08793802499804, "count": 63445, "is_parallel": true, "self": 18.43567665198043, "children": { "_process_rank_one_or_two_observation": { "total": 75.65226137301761, "count": 507560, "is_parallel": true, "self": 75.65226137301761 } } } } } } } } } } }, "trainer_advance": { "total": 666.2441565500048, "count": 63446, "self": 2.322384149055779, "children": { "process_trajectory": { "total": 123.12036692195215, "count": 63446, "self": 122.80594988995244, "children": { "RLTrainer._checkpoint": { "total": 0.31441703199971016, "count": 2, "self": 0.31441703199971016 } } }, "_update_policy": { "total": 540.8014054789969, "count": 431, "self": 299.6271436849611, "children": { "TorchPPOOptimizer.update": { "total": 241.17426179403583, "count": 22848, "self": 241.17426179403583 } } } } } } }, "trainer_threads": { "total": 8.799997885944322e-07, "count": 1, "self": 8.799997885944322e-07 }, "TrainerController._save_models": { "total": 0.07988617699993483, "count": 1, "self": 0.0011133799998788163, "children": { "RLTrainer._checkpoint": { "total": 0.07877279700005602, "count": 1, "self": 0.07877279700005602 } } } } } } }