{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6620796918869019, "min": 0.6620796918869019, "max": 1.4667741060256958, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19978.916015625, "min": 19960.2265625, "max": 44496.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20519033074378967, "min": -0.17344701290130615, "max": 0.20654046535491943, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.528724670410156, "min": -41.10694122314453, "max": 52.874359130859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.3986117839813232, "min": -0.06036427989602089, "max": 1.3986117839813232, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 358.04461669921875, "min": -15.030705451965332, "max": 358.04461669921875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0692680958971588, "min": 0.06470004747573399, "max": 0.07248837278178268, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9697533425602232, "min": 0.49441283309398, "max": 1.0483101284513465, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.3603130001878022, "min": 8.47830240978031e-05, "max": 0.3603130001878022, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 5.044382002629231, "min": 0.0011869623373692434, "max": 5.044382002629231, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.609126035085715e-06, "min": 7.609126035085715e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001065277644912, "min": 0.0001065277644912, "max": 0.0031178401607199996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253634285714286, "min": 0.10253634285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355088, "min": 1.3691136000000002, "max": 2.3588663, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026338065142857153, "min": 0.00026338065142857153, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036873291200000013, "min": 0.0036873291200000013, "max": 0.103944072, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013422289863228798, "min": 0.013422289863228798, "max": 0.43161314725875854, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18791206181049347, "min": 0.18791206181049347, "max": 3.021291971206665, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 636.6086956521739, "min": 611.156862745098, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29284.0, "min": 15984.0, "max": 32901.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0154477882644404, "min": -1.0000000521540642, "max": 1.0154477882644404, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 46.71059826016426, "min": -32.000001668930054, "max": 48.823198437690735, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0154477882644404, "min": -1.0000000521540642, "max": 1.0154477882644404, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 46.71059826016426, "min": -32.000001668930054, "max": 48.823198437690735, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08974283203133382, "min": 0.08752535250467047, "max": 8.214335225522518, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.128170273441356, "min": 4.128170273441356, "max": 131.4293636083603, "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": "1684171069", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684174108" }, "total": 3039.81514055, "count": 1, "self": 0.577137847999893, "children": { "run_training.setup": { "total": 0.08268272599980264, "count": 1, "self": 0.08268272599980264 }, "TrainerController.start_learning": { "total": 3039.155319976, "count": 1, "self": 2.2148949709726367, "children": { "TrainerController._reset_env": { "total": 1.527361185000018, "count": 1, "self": 1.527361185000018 }, "TrainerController.advance": { "total": 3035.3060140780276, "count": 63286, "self": 2.2841829730673453, "children": { "env_step": { "total": 1866.624345296985, "count": 63286, "self": 1726.2285102259793, "children": { "SubprocessEnvManager._take_step": { "total": 139.0217970800138, "count": 63286, "self": 6.890456470957815, "children": { "TorchPolicy.evaluate": { "total": 132.131340609056, "count": 62563, "self": 132.131340609056 } } }, "workers": { "total": 1.3740379909918374, "count": 63286, "self": 0.0, "children": { "worker_root": { "total": 3032.9997046860194, "count": 63286, "is_parallel": true, "self": 1470.041201775975, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036436600000797625, "count": 1, "is_parallel": true, "self": 0.0010930240000561753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025506360000235873, "count": 8, "is_parallel": true, "self": 0.0025506360000235873 } } }, "UnityEnvironment.step": { "total": 0.11045893999994405, "count": 1, "is_parallel": true, "self": 0.0008369439999569295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006263870000111638, "count": 1, "is_parallel": true, "self": 0.0006263870000111638 }, "communicator.exchange": { "total": 0.10653362799985189, "count": 1, "is_parallel": true, "self": 0.10653362799985189 }, "steps_from_proto": { "total": 0.0024619810001240694, "count": 1, "is_parallel": true, "self": 0.0005753020000156539, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018866790001084155, "count": 8, "is_parallel": true, "self": 0.0018866790001084155 } } } } } } }, "UnityEnvironment.step": { "total": 1562.9585029100444, "count": 63285, "is_parallel": true, "self": 44.509151482126526, "children": { "UnityEnvironment._generate_step_input": { "total": 24.205985459940848, "count": 63285, "is_parallel": true, "self": 24.205985459940848 }, "communicator.exchange": { "total": 1362.4870685549581, "count": 63285, "is_parallel": true, "self": 1362.4870685549581 }, "steps_from_proto": { "total": 131.75629741301896, "count": 63285, "is_parallel": true, "self": 27.93870645329048, "children": { "_process_rank_one_or_two_observation": { "total": 103.81759095972848, "count": 506280, "is_parallel": true, "self": 103.81759095972848 } } } } } } } } } } }, "trainer_advance": { "total": 1166.3974858079755, "count": 63286, "self": 4.097018040994044, "children": { "process_trajectory": { "total": 144.0392915559869, "count": 63286, "self": 143.7545519799869, "children": { "RLTrainer._checkpoint": { "total": 0.28473957599999267, "count": 2, "self": 0.28473957599999267 } } }, "_update_policy": { "total": 1018.2611762109946, "count": 434, "self": 419.7806967830088, "children": { "TorchPPOOptimizer.update": { "total": 598.4804794279858, "count": 22914, "self": 598.4804794279858 } } } } } } }, "trainer_threads": { "total": 1.2210002751089633e-06, "count": 1, "self": 1.2210002751089633e-06 }, "TrainerController._save_models": { "total": 0.10704852099934214, "count": 1, "self": 0.0015458779998880345, "children": { "RLTrainer._checkpoint": { "total": 0.10550264299945411, "count": 1, "self": 0.10550264299945411 } } } } } } }