Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained. They have been shown to perform relatively well compared to other exploration strategies. Further, model-based approaches, such as encoder-decoder models have been used successfully for next frame prediction given previous frames. This paper proposes to integrate the model-free Q-ensembles and model-based approaches with the hope of compounding the benefits of both and achieving superior exploration as a result. Results show that a model-based trajectory memory approach when combined with Q-ensembles produces superior performance when compared to only using Q-ensembles.
iPINNER: An Iterative Physics-Informed Neural Network with Ensemble Kalman Filter
School of Electrical and Computer Engineering（电气与计算机工程学院）；Purdue University（普渡大学）；Department of Mathematics（数学系）；Department of Mathematics and School of Mechanical Engineering（数学系和机械工程学院）
Physics-Informed Teacher-Student Ensemble Learning for Traffic State Estimation with a Varying Speed Limit Scenario
Department of Building, Civil and Environmental Engineering, Concordia University（康科迪亚大学建筑、土木和环境工程系）；Urban Artificial Intelligence Laboratory, University of Florida（佛罗里达大学城市人工智能实验室）；Department of Civil, Environmental and Construction Engineering, University of Central Florida（中央佛罗里达大学土木、环境和建设工程系）
Interpretable Physics-Informed Load Forecasting for U.S. Grid Resilience: SHAP-Guided Ensemble Validation in Hybrid Deep Learning Under Extreme Weather
1Dept. of Computer Science, Midwestern State University, Dallas, TX, USA 2O\&M Analytics, AES Clean Energy, The AES Corporation, Louisville, CO, USA 3Dept. of Information；Communication Engineering, Pabna University of Science
AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
Stanford University（斯坦福大学）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
深度强化学习（RL）代理使用的探索机制在确定其样本效率方面起着关键作用。因此，改进随机探索对于解决具有稀疏奖励的长时间任务至关重要。我们建议利用一个合奏的部分解决方案作为教师，指导代理人的探索与行动建议在整个培训。虽然以前已经研究过与教师一起学习的设置，但我们提出的方法- Actor-Critic with Teacher Ensembles（AC-Teach）-是第一个与次优教师的合奏一起工作的方法，这些教师可能只解决了问题的一部分或相互矛盾，形成了与广泛的教师合奏兼容的统一算法解决方案。AC-Teach利用教师和学生行为的预期结果的概率表示来指导探索，减少抖动，并适应学习者动态变化的质量。我们评估了一个变体的AC-教，指导学习贝叶斯DDPG代理的三个任务-路径跟踪，机器人拾取和放置，机器人立方体清扫使用钩子-并表明，它大大提高了采样效率在一组基线，无论是我们的目标场景不受约束的次优教师和更容易设置与最佳或单一的教师。更多结果和视频请访问https://sites.google.com/view/acteach/home。
On the Effectiveness of Mode Exploration in Bayesian Model Averaging for Neural Networks
Massachusetts Institute of Technology, Lincoln Laboratory（麻省理工学院林肯实验室）
已经出现了在监督学习设置中使用深度神经网络来产生校准的预测概率的多种技术，这些技术利用方法来集成在循环训练或从多个随机起始点（深度集成）进行训练期间发现的不同解决方案。然而，只有有限数量的工作已经调查了探索每个不同的解决方案（后验模式）周围的局部区域的效用。我们在CIFAR-10数据集上使用三种众所周知的深度架构，评估了几种简单的方法，用于探索权重空间的局部区域，包括Brier评分、准确性和预期校准误差。我们考虑贝叶斯推理技术（变分推理和应用于softmax输出层的Hamilton Monte Carlo）以及利用接近最优的随机梯度下降轨迹。虽然将单独的模式添加到合奏统一提高性能，我们表明，这里考虑的简单模式探索方法产生很少或没有改善没有模式探索合奏。
Constrained Ensemble Exploration for Unsupervised Skill Discovery
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shenzhen Research Institute of Northwestern Polytechnical University（西北工业大学深圳研究院）；Hong Kong University of Science and Technology（香港科技大学）；Tencent（腾讯）；East China University of Science and Technology（华东理工大学）；The Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））
Ensemble learning of the atrial fiber orientation with physics-informed neural networks
Pontificia Universidad Católica de Chile（智利天主教大学）；University of Trento（特伦托大学）；Università della Svizzera italiana（瑞士意大利语大学）；Institute for Biological and Medical Engineering（生物与医学工程研究所）；Millennium Institute for Intelligent Healthcare Engineering, iHEALTH（千禧智能医疗工程研究所iHEALTH）
Reactivity-Informed Machine Learning for Performance Prediction and Design Space Exploration of Alkali-Activated Slag
Department of Civil and Environmental Engineering, Rice University（Rice大学土木与环境工程系）；Rice Advanced Materials Institute, Rice University（Rice大学先进材料研究所）；Ken Kennedy Institute, Rice University（Rice大学肯尼迪研究所）
Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Virginia（弗吉尼亚大学）；University of Tübingen（蒂宾根大学）
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）；Carnegie Mellon University（卡内基梅隆大学）；King’s College London（伦敦国王学院）；Queen Mary University London（伦敦玛丽女王大学）；Microsoft Research Cambridge（微软研究院剑桥分部）
Physics-Informed Neural Networks for Methane Sorption: Cross-Gas Transfer Learning, Ensemble Collapse Under Physics Constraints, and Monte Carlo Dropout Uncertainty Quantification
Environmental Geosciences, Department of Geosciences, University of Oslo（奥斯陆大学环境地质学系）；National Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing)（中国石油大学（北京）石油资源与工程国家级重点实验室）；College of Geosciences, China University of Petroleum (Beijing)（中国石油大学（北京）地质学院）；State Key Laboratory of Coal Mine Disaster Prevention and Control, China University of Mining and Technology（中国矿业大学煤矿灾害防治控制国家重点实验室）；The Lyell Centre, Heriot-Watt University（赫瑞斯泰大学利尔中心）；Subsurface Energy Transition and Innovation Centre, Heriot-Watt University（赫瑞斯泰大学地下能源转型与创新中心）
