著者: Bolin Gao , Lacra Pavel - arXiv 2017 被引用: 260
In this paper, we utilize results from convex analysis and monotone operator theory to derive additional properties of the softmax function that have not yet been covered in the existing literature. In particular, we show that the softmax function is the monotone gradient map of the log-sum-exp function. By exploiting this connection, we show that the inverse temperature parameter determines the Lipschitz and co-coercivity properties of the softmax function. We then demonstrate the usefulness of these properties through an application in game-theoretic reinforcement learning.
✨ ログイン状態を確認しています… PDF 被引用 BibTeX を表示 BibTeX を閉じる BibTeX を表示 引用
Individual Choice Behavior: A Theoretical… Individual Choice Behavior: A Theoretical Analysis. Reinforcement learning - an introduction Reinforcement learning - an introduction Evolutionary Games and Population Dynamics Evolutionary Games and Population Dynamics Learning in perturbed asymmetric games Learning in perturbed asymmetric games Individual Q-Learning in Normal Form Games Individual Q-Learning in Normal Form Games Population Games And Evolutionary Dynamics Population Games And Evolutionary Dynamics Should I stay or should I go? How the human… Should I stay or should I go? How the human brain manages the trade-off between exploitation and exploration The projection dynamic and the replicator… The projection dynamic and the replicator dynamic Evolutionary Game Theory Evolutionary Game Theory Convex Analysis and Monotone Operator Theor… Convex Analysis and Monotone Operator Theory in Hilbert Spaces Introductory Lectures on Convex Optimization: A… Introductory Lectures on Convex Optimization: A Basic Course Evolutionary Dynamics of Multi-Agent Learning: A… Evolutionary Dynamics of Multi-Agent Learning: A Survey openalex_id:w3113374047 openalex_id:w3113374047 AlphaPose: Whole-Body Regional Multi-Person… AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time Lipschitz Continuity in Model-based… Lipschitz Continuity in Model-based Reinforcement Learning Q-Learning Algorithms: A Comprehensive… Q-Learning Algorithms: A Comprehensive Classification and Applications BrainMRNet: Brain tumor detection using magneti… BrainMRNet: Brain tumor detection using magnetic resonance images with a novel convolutional neural network model Capsule Networks - A survey Capsule Networks - A survey Incentive Mechanism for Multiple Cooperative… Incentive Mechanism for Multiple Cooperative Tasks with Compatible Users in Mobile Crowd Sensing via Online Communities DeeperGCN: All You Need to Train Deeper GCNs DeeperGCN: All You Need to Train Deeper GCNs Fast Transformers with Clustered Attention Fast Transformers with Clustered Attention Exploration-Exploitation in Multi-Agent Learning… Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory Detecting the Stages of Alzheimer’s Disease wit… Detecting the Stages of Alzheimer’s Disease with Pre-trained Deep Learning Architectures The Devil in Linear Transformer The Devil in Linear Transformer On the Properties of the Softmax Function with… On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning 過去の参考文献 中心の論文 この論文を引用する論文 古い 新しい ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。
