{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36790165305137634, "min": 0.36790165305137634, "max": 1.4527993202209473, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11048.822265625, "min": 11048.822265625, "max": 44072.12109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989873.0, "min": 29916.0, "max": 989873.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989873.0, "min": 29916.0, "max": 989873.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5821087956428528, "min": -0.09952457994222641, "max": 0.5821087956428528, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 160.6620330810547, "min": -23.88589859008789, "max": 161.44308471679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.017392752692103386, "min": -0.017392752692103386, "max": 0.2588585615158081, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.8003997802734375, "min": -4.8003997802734375, "max": 61.34947967529297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06924913545039349, "min": 0.06526466551112403, "max": 0.07268454584257034, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9694878963055088, "min": 0.49582416391610323, "max": 1.0892607890806782, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016143688609493743, "min": 0.00016901287474012255, "max": 0.016143688609493743, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2260116405329124, "min": 0.002197167371621593, "max": 0.23150508842424158, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.694668863714287e-06, "min": 7.694668863714287e-06, "max": 0.0002952344587313714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010772536409200001, "min": 0.00010772536409200001, "max": 0.0034926439357853994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256485714285714, "min": 0.10256485714285714, "max": 0.1984114857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.435908, "min": 1.3888804, "max": 2.5277534, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026622922857142865, "min": 0.00026622922857142865, "max": 0.009841307422857142, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003727209200000001, "min": 0.003727209200000001, "max": 0.11643503853999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011082830838859081, "min": 0.011082830838859081, "max": 0.421742707490921, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15515963733196259, "min": 0.15515963733196259, "max": 2.9521989822387695, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 329.16470588235296, "min": 329.16470588235296, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27979.0, "min": 16715.0, "max": 32060.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6259069541512534, "min": -0.9998667180538178, "max": 1.6494755861235828, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.8279980570078, "min": -29.996001541614532, "max": 143.38999827206135, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6259069541512534, "min": -0.9998667180538178, "max": 1.6494755861235828, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.8279980570078, "min": -29.996001541614532, "max": 143.38999827206135, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.037290735440978474, "min": 0.037290735440978474, "max": 7.583517309497385, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.207003247924149, "min": 3.207003247924149, "max": 128.91979426145554, "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": "1743506320", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743508610" }, "total": 2290.1570602189995, "count": 1, "self": 0.4928448219998245, "children": { "run_training.setup": { "total": 0.019891193000148633, "count": 1, "self": 0.019891193000148633 }, "TrainerController.start_learning": { "total": 2289.6443242039995, "count": 1, "self": 1.3263250610843897, "children": { "TrainerController._reset_env": { "total": 2.1867899179999313, "count": 1, "self": 2.1867899179999313 }, "TrainerController.advance": { "total": 2286.0368939239147, "count": 63836, "self": 1.3506672668959254, "children": { "env_step": { "total": 1609.9045016140353, "count": 63836, "self": 1456.3182849930633, "children": { "SubprocessEnvManager._take_step": { "total": 152.80572225597575, "count": 63836, "self": 4.443385854026701, "children": { "TorchPolicy.evaluate": { "total": 148.36233640194905, "count": 62576, "self": 148.36233640194905 } } }, "workers": { "total": 0.7804943649962297, "count": 63836, "self": 0.0, "children": { "worker_root": { "total": 2284.5502706049615, "count": 63836, "is_parallel": true, "self": 938.3578754609368, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019329300000663352, "count": 1, "is_parallel": true, "self": 0.0006928999998763175, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012400300001900177, "count": 8, "is_parallel": true, "self": 0.0012400300001900177 } } }, "UnityEnvironment.step": { "total": 0.044992246999981944, "count": 1, "is_parallel": true, "self": 0.0005177250002361689, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047221799991348234, "count": 1, "is_parallel": true, "self": 0.00047221799991348234 }, "communicator.exchange": { "total": 0.04244797199999084, "count": 1, "is_parallel": true, "self": 0.04244797199999084 }, "steps_from_proto": { "total": 0.0015543319998414518, "count": 1, "is_parallel": true, "self": 0.00034392499969726487, "children": { "_process_rank_one_or_two_observation": { "total": 0.001210407000144187, "count": 8, "is_parallel": true, "self": 0.001210407000144187 } } } } } } }, "UnityEnvironment.step": { "total": 1346.1923951440247, "count": 63835, "is_parallel": true, "self": 31.435448783137417, "children": { "UnityEnvironment._generate_step_input": { "total": 22.68567185801112, "count": 63835, "is_parallel": true, "self": 22.68567185801112 }, "communicator.exchange": { "total": 1198.7369468719958, "count": 63835, "is_parallel": true, "self": 1198.7369468719958 }, "steps_from_proto": { "total": 93.33432763088035, "count": 63835, "is_parallel": true, "self": 18.344247559069345, "children": { "_process_rank_one_or_two_observation": { "total": 74.99008007181101, "count": 510680, "is_parallel": true, "self": 74.99008007181101 } } } } } } } } } } }, "trainer_advance": { "total": 674.7817250429835, "count": 63836, "self": 2.562165308979502, "children": { "process_trajectory": { "total": 122.50634277000427, "count": 63836, "self": 122.30369217900397, "children": { "RLTrainer._checkpoint": { "total": 0.20265059100029248, "count": 2, "self": 0.20265059100029248 } } }, "_update_policy": { "total": 549.7132169639997, "count": 453, "self": 301.57510132997663, "children": { "TorchPPOOptimizer.update": { "total": 248.13811563402305, "count": 22794, "self": 248.13811563402305 } } } } } } }, "trainer_threads": { "total": 8.260003596660681e-07, "count": 1, "self": 8.260003596660681e-07 }, "TrainerController._save_models": { "total": 0.09431447499991918, "count": 1, "self": 0.001646542999878875, "children": { "RLTrainer._checkpoint": { "total": 0.09266793200004031, "count": 1, "self": 0.09266793200004031 } } } } } } }