Gaussian Policy

Gaussian policies, probability distributions used to model actions in reinforcement learning (RL), are a central focus in continuous control tasks, aiming to optimize agent behavior by learning optimal action selection strategies. Current research emphasizes improving the efficiency and robustness of Gaussian policy optimization, exploring techniques like entropy regularization and alternative model architectures (e.g., Beta distributions) to address limitations such as unbounded action spaces and suboptimal exploration. These advancements are significant for various applications, including robotics, finance, and healthcare, where efficient and reliable continuous control is crucial for optimal decision-making.

Papers

September 7, 2024

Reward-Directed Score-Based Diffusion Models via q-Learning
Xuefeng Gao, Jiale Zha, Xun Yu Zhou
Optimal Policy Score Based Diffusion Model Entropy Regularized Gaussian Policy

May 25, 2024

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
Shutong Ding, Ke Hu, Zhenhao Zhang, Kan Ren, Weinan Zhang, Jingyi Yu, Jingya Wang, Ye Shi
Reinforcement Learning Diffusion Policy Gaussian Policy

March 25, 2024

Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games
Muhammad Aneeq uz Zaman, Shubham Aggarwal, Melih Bastopcu, Tamer Başar
Multi Agent Nash Equilibrium Policy OpTimization Policy Optimization Gaussian Policy Linear Quadratic

December 19, 2023

Learning Merton's Strategies in an Incomplete Market: Recursive Entropy Regularization and Biased Gaussian Exploration
Min Dai, Yuchao Dong, Yanwei Jia, Xun Yu Zhou
Reinforcement Learning Policy Gradient General Strategy Utility Maximization Stochastic Volatility Optimal Portfolio Gaussian Policy Market Equilibrium

May 11, 2023

Policy Gradient Algorithms Implicitly Optimize by Continuation
Adrien Bolland, Gilles Louppe, Damien Ernst
Reinforcement Learning Policy Gradient Deterministic Policy Policy Gradient Algorithm Direct Policy Gaussian Policy

January 21, 2023

Quasi-optimal Reinforcement Learning with Continuous Actions
Yuhan Li, Wenzhuo Zhou, Ruoqing Zhu
Reinforcement Learning Near Optimal Optimal Learning Optimal Reinforcement Learning Continuous Action Gaussian Policy

November 1, 2022

Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems
Michael Giegrich, Christoph Reisinger, Yufei Zhang
Policy Gradient Early Stage Convergence Gaussian Policy

January 20, 2022

A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learning
Yuan Tian, Minghao Han, Chetan Kulkarni, Olga Fink
Reinforcement Learning Deep Reinforcement Learning Power Allocation Softmax Policy Gaussian Policy Optimal Operation

November 3, 2021

Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution
Irving G. B. Petrazzini, Eric A. Antonelo
Reinforcement Learning Policy Gradient Action Space Proximal Policy Optimization Stochastic Policy Beta Distribution Gaussian Policy

Gaussian Policy

Papers

Reward-Directed Score-Based Diffusion Models via q-Learning

Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization

Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games

Learning Merton's Strategies in an Incomplete Market: Recursive Entropy Regularization and Biased Gaussian Exploration

Policy Gradient Algorithms Implicitly Optimize by Continuation

Quasi-optimal Reinforcement Learning with Continuous Actions

Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems

A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learning

Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution