{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7327338457107544, "min": 0.7327338457107544, "max": 1.497498631477356, "count": 18 }, "Pyramids.Policy.Entropy.sum": { "value": 22146.1484375, "min": 22146.1484375, "max": 45428.1171875, "count": 18 }, "Pyramids.Step.mean": { "value": 539899.0, "min": 29952.0, "max": 539899.0, "count": 18 }, "Pyramids.Step.sum": { "value": 539899.0, "min": 29952.0, "max": 539899.0, "count": 18 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34403565526008606, "min": -0.09342267364263535, "max": 0.34403565526008606, "count": 18 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.48137664794922, "min": -22.42144203186035, "max": 90.48137664794922, "count": 18 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.014637668617069721, "min": 0.005799040663987398, "max": 0.37396278977394104, "count": 18 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.8497068881988525, "min": 1.513549566268921, "max": 88.62918090820312, "count": 18 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06890976203569499, "min": 0.06579626566044355, "max": 0.07551052829854754, "count": 18 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9647366684997298, "min": 0.49923934032367784, "max": 1.0787221396943398, "count": 18 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013737173203827254, "min": 0.0002445777497493757, "max": 0.013737173203827254, "count": 18 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19232042485358156, "min": 0.002201199747744381, "max": 0.19232042485358156, "count": 18 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00024748909607506906, "min": 0.00024748909607506906, "max": 0.00029838354339596195, "count": 18 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0034648473450509666, "min": 0.0020691136102954665, "max": 0.0038475524174826003, "count": 18 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18249635952380955, "min": 0.18249635952380955, "max": 0.19946118095238097, "count": 18 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5549490333333336, "min": 1.3897045333333333, "max": 2.7825174000000006, "count": 18 }, "Pyramids.Policy.Beta.mean": { "value": 0.008251386316428572, "min": 0.008251386316428572, "max": 0.009946171977142856, "count": 18 }, "Pyramids.Policy.Beta.sum": { "value": 0.11551940843, "min": 0.06897148288, "max": 0.12827348826, "count": 18 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013684570789337158, "min": 0.013684570789337158, "max": 0.30307528376579285, "count": 18 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19158399105072021, "min": 0.19158399105072021, "max": 2.1215269565582275, "count": 18 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 481.2096774193548, "min": 481.2096774193548, "max": 999.0, "count": 18 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29835.0, "min": 15984.0, "max": 32904.0, "count": 18 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.396108169047559, "min": -1.0000000521540642, "max": 1.396108169047559, "count": 18 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 85.16259831190109, "min": -32.000001668930054, "max": 85.16259831190109, "count": 18 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.396108169047559, "min": -1.0000000521540642, "max": 1.396108169047559, "count": 18 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 85.16259831190109, "min": -32.000001668930054, "max": 85.16259831190109, "count": 18 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06789128810761794, "min": 0.06789128810761794, "max": 5.5536161763593554, "count": 18 }, "Pyramids.Policy.RndReward.sum": { "value": 4.141368574564694, "min": 4.141368574564694, "max": 88.85785882174969, "count": 18 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 18 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 18 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711100966", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711102120" }, "total": 1153.774096381, "count": 1, "self": 0.39394427799993537, "children": { "run_training.setup": { "total": 0.06171204600002511, "count": 1, "self": 0.06171204600002511 }, "TrainerController.start_learning": { "total": 1153.3184400569999, "count": 1, "self": 0.7722146630057978, "children": { "TrainerController._reset_env": { "total": 2.8856104649998997, "count": 1, "self": 2.8856104649998997 }, "TrainerController.advance": { "total": 1149.5283519049942, "count": 34164, "self": 0.8193373759779661, "children": { "env_step": { "total": 799.139966681998, "count": 34164, "self": 720.654607089023, "children": { "SubprocessEnvManager._take_step": { "total": 77.9950567069667, "count": 34164, "self": 2.7255543909684548, "children": { "TorchPolicy.evaluate": { "total": 75.26950231599824, "count": 33819, "self": 75.26950231599824 } } }, "workers": { "total": 0.4903028860082941, "count": 34163, "self": 0.0, "children": { "worker_root": { "total": 1150.3545967490136, "count": 34163, "is_parallel": true, "self": 499.0688235920337, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006152721999910682, "count": 1, "is_parallel": true, "self": 0.004550983999820346, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016017380000903358, "count": 8, "is_parallel": true, "self": 0.0016017380000903358 } } }, "UnityEnvironment.step": { "total": 0.11271373600004608, "count": 1, "is_parallel": true, "self": 0.0006167540000205918, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004589960000203064, "count": 1, "is_parallel": true, "self": 0.0004589960000203064 }, "communicator.exchange": { "total": 0.10999931200001356, "count": 1, "is_parallel": true, "self": 0.10999931200001356 }, "steps_from_proto": { "total": 0.0016386739999916244, "count": 1, "is_parallel": true, "self": 0.00039619099993615237, "children": { "_process_rank_one_or_two_observation": { "total": 0.001242483000055472, "count": 8, "is_parallel": true, "self": 0.001242483000055472 } } } } } } }, "UnityEnvironment.step": { "total": 651.2857731569799, "count": 34162, "is_parallel": true, "self": 19.38184330401282, "children": { "UnityEnvironment._generate_step_input": { "total": 13.782417990987142, "count": 34162, "is_parallel": true, "self": 13.782417990987142 }, "communicator.exchange": { "total": 559.5342678620036, "count": 34162, "is_parallel": true, "self": 559.5342678620036 }, "steps_from_proto": { "total": 58.587243999976295, "count": 34162, "is_parallel": true, "self": 11.928019258943664, "children": { "_process_rank_one_or_two_observation": { "total": 46.65922474103263, "count": 273296, "is_parallel": true, "self": 46.65922474103263 } } } } } } } } } } }, "trainer_advance": { "total": 349.5690478470184, "count": 34163, "self": 1.429292956997756, "children": { "process_trajectory": { "total": 70.32915233902156, "count": 34163, "self": 70.06635567602154, "children": { "RLTrainer._checkpoint": { "total": 0.26279666300001736, "count": 1, "self": 0.26279666300001736 } } }, "_update_policy": { "total": 277.8106025509991, "count": 224, "self": 165.37229254999954, "children": { "TorchPPOOptimizer.update": { "total": 112.43831000099954, "count": 12399, "self": 112.43831000099954 } } } } } } }, "trainer_threads": { "total": 1.4859999737382168e-06, "count": 1, "self": 1.4859999737382168e-06 }, "TrainerController._save_models": { "total": 0.1322615379999661, "count": 1, "self": 0.0020812499999465217, "children": { "RLTrainer._checkpoint": { "total": 0.13018028800001957, "count": 1, "self": 0.13018028800001957 } } } } } } }