{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4890124201774597, "min": 0.4871698021888733, "max": 1.497849941253662, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14623.427734375, "min": 14623.427734375, "max": 45438.77734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989872.0, "min": 29952.0, "max": 989872.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3821113705635071, "min": -0.12042415142059326, "max": 0.4299923777580261, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.6416244506836, "min": -29.022220611572266, "max": 116.09793853759766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03452696651220322, "min": -0.03452696651220322, "max": 0.7002473473548889, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -9.184173583984375, "min": -9.184173583984375, "max": 165.9586181640625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06565161668503114, "min": 0.06472854698150818, "max": 0.07277536266258362, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.919122633590436, "min": 0.48718782245056386, "max": 1.0381515710032547, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012553311362521411, "min": 0.00024897427902019937, "max": 0.01297823557262022, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17574635907529976, "min": 0.002987691348242392, "max": 0.18169529801668308, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.666618873064285e-06, "min": 7.666618873064285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001073326642229, "min": 0.0001073326642229, "max": 0.0032603837132055002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255550714285715, "min": 0.10255550714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357771000000001, "min": 1.3691136000000002, "max": 2.3867945, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002652951635714286, "min": 0.0002652951635714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037141322900000003, "min": 0.0037141322900000003, "max": 0.10870077055, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009146452881395817, "min": 0.009146452881395817, "max": 0.47849056124687195, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12805034220218658, "min": 0.12805034220218658, "max": 3.3494338989257812, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 473.4754098360656, "min": 432.6617647058824, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28882.0, "min": 15984.0, "max": 32881.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3625507950782776, "min": -1.0000000521540642, "max": 1.4790705629788778, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 83.11559849977493, "min": -32.000001668930054, "max": 100.61259798705578, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3625507950782776, "min": -1.0000000521540642, "max": 1.4790705629788778, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 83.11559849977493, "min": -32.000001668930054, "max": 100.61259798705578, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04494388605139722, "min": 0.043409924179030265, "max": 10.492835386656225, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7415770491352305, "min": 2.7415770491352305, "max": 167.8853661864996, "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": "1787063713", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/content/mlagents310/bin/mlagents-learn ./ml-agents/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": "1787066547" }, "total": 2834.269838649, "count": 1, "self": 0.5288361100006114, "children": { "run_training.setup": { "total": 0.027758845999869664, "count": 1, "self": 0.027758845999869664 }, "TrainerController.start_learning": { "total": 2833.7132436929996, "count": 1, "self": 1.6961907119821262, "children": { "TrainerController._reset_env": { "total": 2.3100528109998777, "count": 1, "self": 2.3100528109998777 }, "TrainerController.advance": { "total": 2829.619582757018, "count": 63411, "self": 1.7855552890196122, "children": { "env_step": { "total": 2108.8993917929974, "count": 63411, "self": 1923.6632750990739, "children": { "SubprocessEnvManager._take_step": { "total": 184.15169360293703, "count": 63411, "self": 5.659447369906047, "children": { "TorchPolicy.evaluate": { "total": 178.49224623303098, "count": 62564, "self": 178.49224623303098 } } }, "workers": { "total": 1.0844230909865473, "count": 63411, "self": 0.0, "children": { "worker_root": { "total": 2827.2394030829946, "count": 63411, "is_parallel": true, "self": 1050.5821578619427, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020644670000820042, "count": 1, "is_parallel": true, "self": 0.0006295600003340951, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014349069997479091, "count": 8, "is_parallel": true, "self": 0.0014349069997479091 } } }, "UnityEnvironment.step": { "total": 0.05796209400000407, "count": 1, "is_parallel": true, "self": 0.0007104570001956745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005380140000852407, "count": 1, "is_parallel": true, "self": 0.0005380140000852407 }, "communicator.exchange": { "total": 0.054655366999895705, "count": 1, "is_parallel": true, "self": 0.054655366999895705 }, "steps_from_proto": { "total": 0.002058255999827452, "count": 1, "is_parallel": true, "self": 0.0004437629995663883, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016144930002610636, "count": 8, "is_parallel": true, "self": 0.0016144930002610636 } } } } } } }, "UnityEnvironment.step": { "total": 1776.6572452210519, "count": 63410, "is_parallel": true, "self": 39.855736947260766, "children": { "UnityEnvironment._generate_step_input": { "total": 28.404749949941333, "count": 63410, "is_parallel": true, "self": 28.404749949941333 }, "communicator.exchange": { "total": 1572.8477439518722, "count": 63410, "is_parallel": true, "self": 1572.8477439518722 }, "steps_from_proto": { "total": 135.5490143719776, "count": 63410, "is_parallel": true, "self": 27.167718703889477, "children": { "_process_rank_one_or_two_observation": { "total": 108.38129566808811, "count": 507280, "is_parallel": true, "self": 108.38129566808811 } } } } } } } } } } }, "trainer_advance": { "total": 718.9346356750013, "count": 63411, "self": 3.157804953989398, "children": { "process_trajectory": { "total": 129.78335699500326, "count": 63411, "self": 129.56936665900298, "children": { "RLTrainer._checkpoint": { "total": 0.21399033600027906, "count": 2, "self": 0.21399033600027906 } } }, "_update_policy": { "total": 585.9934737260087, "count": 439, "self": 314.78817231297944, "children": { "TorchPPOOptimizer.update": { "total": 271.20530141302925, "count": 22800, "self": 271.20530141302925 } } } } } } }, "trainer_threads": { "total": 1.050999344442971e-06, "count": 1, "self": 1.050999344442971e-06 }, "TrainerController._save_models": { "total": 0.08741636200011271, "count": 1, "self": 0.0010888890001297113, "children": { "RLTrainer._checkpoint": { "total": 0.086327472999983, "count": 1, "self": 0.086327472999983 } } } } } } }