{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38789305090904236, "min": 0.38789305090904236, "max": 1.391270637512207, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 11618.1728515625, "min": 11618.1728515625, "max": 42205.5859375, "count": 3 }, "Pyramids.Step.mean": { "value": 89881.0, "min": 29952.0, "max": 89881.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89881.0, "min": 29952.0, "max": 89881.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07616780698299408, "min": -0.07616780698299408, "max": 0.074172742664814, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -18.2802734375, "min": -18.2802734375, "max": 17.57893943786621, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.6363086700439453, "min": 0.6363086700439453, "max": 1.2107458114624023, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 152.71408081054688, "min": 152.71408081054688, "max": 291.78973388671875, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751920362323628, "min": 0.06723118156932771, "max": 0.07113847050289944, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6076728326091265, "min": 0.4979692935202961, "max": 0.6076728326091265, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0011957605451968858, "min": 0.0011957605451968858, "max": 0.05458596548216941, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.010761844906771973, "min": 0.010761844906771973, "max": 0.38210175837518584, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.500240833255555e-05, "min": 7.500240833255555e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000675021674993, "min": 0.000675021674993, "max": 0.0017605441131519999, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12500077777777782, "min": 0.12500077777777782, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.1250070000000003, "min": 1.1250070000000003, "max": 1.384667, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.0025075777000000007, "min": 0.0025075777000000007, "max": 0.008385159314285715, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.022568199300000005, "min": 0.022568199300000005, "max": 0.0586961152, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.3921284079551697, "min": 0.3921284079551697, "max": 1.5184694528579712, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.529155731201172, "min": 3.529155731201172, "max": 10.62928581237793, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 991.78125, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31968.0, "min": 15984.0, "max": 31968.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -0.9302500516641885, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -32.000001668930054, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -0.9302500516641885, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -32.000001668930054, "min": -32.000001668930054, "max": -16.000000834465027, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 4.442003672011197, "min": 4.442003672011197, "max": 17.00814649090171, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 142.1441175043583, "min": 142.1441175043583, "max": 425.73938899999484, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1781782548", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781782731" }, "total": 182.91047707500002, "count": 1, "self": 0.5833454269998128, "children": { "run_training.setup": { "total": 0.023958877000040957, "count": 1, "self": 0.023958877000040957 }, "TrainerController.start_learning": { "total": 182.30317277100016, "count": 1, "self": 0.12976940799785552, "children": { "TrainerController._reset_env": { "total": 2.806794840999828, "count": 1, "self": 2.806794840999828 }, "TrainerController.advance": { "total": 179.25624148700263, "count": 6277, "self": 0.13859986199531704, "children": { "env_step": { "total": 150.84365879100255, "count": 6277, "self": 134.67584374200578, "children": { "SubprocessEnvManager._take_step": { "total": 16.08729657899562, "count": 6277, "self": 0.47763296198991156, "children": { "TorchPolicy.evaluate": { "total": 15.609663617005708, "count": 6277, "self": 15.609663617005708 } } }, "workers": { "total": 0.08051847000115231, "count": 6277, "self": 0.0, "children": { "worker_root": { "total": 181.58406250300118, "count": 6277, "is_parallel": true, "self": 58.73259175099656, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025475680001818546, "count": 1, "is_parallel": true, "self": 0.0007192840002971934, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018282839998846612, "count": 8, "is_parallel": true, "self": 0.0018282839998846612 } } }, "UnityEnvironment.step": { "total": 0.09603723199984415, "count": 1, "is_parallel": true, "self": 0.0005754079998041561, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004059779998897284, "count": 1, "is_parallel": true, "self": 0.0004059779998897284 }, "communicator.exchange": { "total": 0.09117324400017424, "count": 1, "is_parallel": true, "self": 0.09117324400017424 }, "steps_from_proto": { "total": 0.003882601999976032, "count": 1, "is_parallel": true, "self": 0.0003818259992840467, "children": { "_process_rank_one_or_two_observation": { "total": 0.0035007760006919852, "count": 8, "is_parallel": true, "self": 0.0035007760006919852 } } } } } } }, "UnityEnvironment.step": { "total": 122.85147075200462, "count": 6276, "is_parallel": true, "self": 3.457731065002463, "children": { "UnityEnvironment._generate_step_input": { "total": 2.42387392999899, "count": 6276, "is_parallel": true, "self": 2.42387392999899 }, "communicator.exchange": { "total": 105.76814214199908, "count": 6276, "is_parallel": true, "self": 105.76814214199908 }, "steps_from_proto": { "total": 11.201723615004084, "count": 6276, "is_parallel": true, "self": 2.3121143960215704, "children": { "_process_rank_one_or_two_observation": { "total": 8.889609218982514, "count": 50208, "is_parallel": true, "self": 8.889609218982514 } } } } } } } } } } }, "trainer_advance": { "total": 28.273982834004755, "count": 6277, "self": 0.17685778699978982, "children": { "process_trajectory": { "total": 10.366786008005647, "count": 6277, "self": 10.366786008005647 }, "_update_policy": { "total": 17.73033903899932, "count": 29, "self": 9.449124662001623, "children": { "TorchPPOOptimizer.update": { "total": 8.281214376997696, "count": 762, "self": 8.281214376997696 } } } } } } }, "trainer_threads": { "total": 8.019999313546577e-07, "count": 1, "self": 8.019999313546577e-07 }, "TrainerController._save_models": { "total": 0.11036623299992243, "count": 1, "self": 0.0010788329998376867, "children": { "RLTrainer._checkpoint": { "total": 0.10928740000008474, "count": 1, "self": 0.10928740000008474 } } } } } } }