{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4578075408935547, "min": 0.4578075408935547, "max": 0.4578075408935547, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 9602.970703125, "min": 9602.970703125, "max": 9602.970703125, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.31481481481484, "min": 326.31481481481484, "max": 326.31481481481484, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 17621.0, "min": 17621.0, "max": 17621.0, "count": 1 }, "Pyramids.Step.mean": { "value": 1019988.0, "min": 1019988.0, "max": 1019988.0, "count": 1 }, "Pyramids.Step.sum": { "value": 1019988.0, "min": 1019988.0, "max": 1019988.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5122177004814148, "min": 0.5122177004814148, "max": 0.5122177004814148, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 93.73583984375, "min": 93.73583984375, "max": 93.73583984375, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012859730049967766, "min": 0.012859730049967766, "max": 0.012859730049967766, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.353330612182617, "min": 2.353330612182617, "max": 2.353330612182617, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5949886622575093, "min": 1.5949886622575093, "max": 1.5949886622575093, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.534399099648, "min": 84.534399099648, "max": 84.534399099648, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5949886622575093, "min": 1.5949886622575093, "max": 1.5949886622575093, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.534399099648, "min": 84.534399099648, "max": 84.534399099648, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020392710874491383, "min": 0.020392710874491383, "max": 0.020392710874491383, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 1.0808136763480434, "min": 1.0808136763480434, "max": 1.0808136763480434, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06944852790049345, "min": 0.06944852790049345, "max": 0.06944852790049345, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.6250367511044411, "min": 0.6250367511044411, "max": 0.6250367511044411, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012599080450686247, "min": 0.012599080450686247, "max": 0.012599080450686247, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11339172405617623, "min": 0.11339172405617623, "max": 0.11339172405617623, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.811014095708062e-06, "min": 2.811014095708062e-06, "max": 2.811014095708062e-06, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.5299126861372555e-05, "min": 2.5299126861372555e-05, "max": 2.5299126861372555e-05, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10093697167755991, "min": 0.10093697167755991, "max": 0.10093697167755991, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.9084327450980392, "min": 0.9084327450980392, "max": 0.9084327450980392, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010360347058823532, "min": 0.00010360347058823532, "max": 0.00010360347058823532, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009324312352941179, "min": 0.0009324312352941179, "max": 0.0009324312352941179, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005835366901010275, "min": 0.005835366901010275, "max": 0.005835366901010275, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05251830071210861, "min": 0.05251830071210861, "max": 0.05251830071210861, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718116846", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718116921" }, "total": 74.91216858000007, "count": 1, "self": 0.629856010000367, "children": { "run_training.setup": { "total": 0.10566821300017182, "count": 1, "self": 0.10566821300017182 }, "TrainerController.start_learning": { "total": 74.17664435699953, "count": 1, "self": 0.0484158110093631, "children": { "TrainerController._reset_env": { "total": 4.1516817900001115, "count": 1, "self": 4.1516817900001115 }, "TrainerController.advance": { "total": 69.88113111299026, "count": 1357, "self": 0.057712297982106975, "children": { "env_step": { "total": 46.601711384003465, "count": 1357, "self": 43.37167667501126, "children": { "SubprocessEnvManager._take_step": { "total": 3.2015309969956434, "count": 1357, "self": 0.14985691299807513, "children": { "TorchPolicy.evaluate": { "total": 3.0516740839975682, "count": 1311, "self": 3.0516740839975682 } } }, "workers": { "total": 0.028503711996563652, "count": 1357, "self": 0.0, "children": { "worker_root": { "total": 74.02612100599708, "count": 1357, "is_parallel": true, "self": 34.46452728899294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003315939999993134, "count": 1, "is_parallel": true, "self": 0.0011167520005983533, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021991879993947805, "count": 8, "is_parallel": true, "self": 0.0021991879993947805 } } }, "UnityEnvironment.step": { "total": 0.06482181900082651, "count": 1, "is_parallel": true, "self": 0.0008052000002862769, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005295939999996335, "count": 1, "is_parallel": true, "self": 0.0005295939999996335 }, "communicator.exchange": { "total": 0.0613688360008382, "count": 1, "is_parallel": true, "self": 0.0613688360008382 }, "steps_from_proto": { "total": 0.0021181889997023973, "count": 1, "is_parallel": true, "self": 0.0004406279995237128, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016775610001786845, "count": 8, "is_parallel": true, "self": 0.0016775610001786845 } } } } } } }, "UnityEnvironment.step": { "total": 39.56159371700414, "count": 1356, "is_parallel": true, "self": 1.0554544790356886, "children": { "UnityEnvironment._generate_step_input": { "total": 0.6629031569609651, "count": 1356, "is_parallel": true, "self": 0.6629031569609651 }, "communicator.exchange": { "total": 35.10112359998402, "count": 1356, "is_parallel": true, "self": 35.10112359998402 }, "steps_from_proto": { "total": 2.7421124810234687, "count": 1356, "is_parallel": true, "self": 0.6471835399688644, "children": { "_process_rank_one_or_two_observation": { "total": 2.0949289410546044, "count": 10848, "is_parallel": true, "self": 2.0949289410546044 } } } } } } } } } } }, "trainer_advance": { "total": 23.22170743100469, "count": 1357, "self": 0.0930325040126263, "children": { "process_trajectory": { "total": 3.5267437559905375, "count": 1357, "self": 3.3817300949904165, "children": { "RLTrainer._checkpoint": { "total": 0.14501366100012092, "count": 1, "self": 0.14501366100012092 } } }, "_update_policy": { "total": 19.601931171001524, "count": 9, "self": 8.272779682001783, "children": { "TorchPPOOptimizer.update": { "total": 11.329151488999742, "count": 432, "self": 11.329151488999742 } } } } } } }, "trainer_threads": { "total": 9.589994078851305e-07, "count": 1, "self": 9.589994078851305e-07 }, "TrainerController._save_models": { "total": 0.09541468400038866, "count": 1, "self": 0.002416738000647456, "children": { "RLTrainer._checkpoint": { "total": 0.0929979459997412, "count": 1, "self": 0.0929979459997412 } } } } } } }