Soft Actor Critic Algorithm

The Soft Actor-Critic (SAC) algorithm is a reinforcement learning method aiming to learn optimal policies by maximizing both expected reward and policy entropy, leading to more robust and exploratory behavior. Current research focuses on extending SAC's applicability to diverse domains, including discrete action spaces, multi-agent systems, and constrained optimization problems, often employing techniques like federated learning and incorporating hints from existing models to improve efficiency. This adaptable algorithm shows promise for various applications, from autonomous control systems in robotics and space exploration to optimizing resource management in industrial settings and agriculture.

Papers

October 19, 2024

Augmented Lagrangian-Based Safe Reinforcement Learning Approach for Distribution System Volt/VAR Control
Guibin Chen
Safe Reinforcement Learning Distribution System Active Distribution Soft Actor Critic Algorithm Based Volt Var Control

September 2, 2024

AI Olympics challenge with Evolutionary Soft Actor Critic
Marco Calì, Alberto Sinigaglia, Niccolò Turcato, Ruggero Carli, Gian Antonio Susto
Practical Algorithm Evolution Strategy Model Free Deep Reinforcement Learning AI City Challenge Soft Actor Critic Algorithm

August 2, 2024

Sustainable Diffusion-based Incentive Mechanism for Generative AI-driven Digital Twins in Industrial Cyber-Physical Systems
Jinbo Wen, Jiawen Kang, Dusit Niyato, Yang Zhang, Shiwen Mao
Digital Twin Generative Artificial Intelligence Cyber Physical System Smart Manufacturing Incentive Mechanism Soft Actor Critic Algorithm Generative Artificial Intelligence Architecture

July 8, 2024

Generalizing soft actor-critic algorithms to discrete action spaces
Le Zhang, Yong Gu, Xin Zhao, Yanshuo Zhang, Shu Zhao, Yifei Jin, Xinxin Wu
Reinforcement Learning Action Space ATARI Game Model Free Algorithm Soft Actor Critic Algorithm

October 11, 2023

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
Zeyang Li, Chuxiong Hu, Yunan Wang, Guojian Zhan, Jie Li, Shengbo Eben Li
Policy Iteration Local Convergence Newton Iteration Soft Actor Critic Algorithm Newton Raphson

July 28, 2023

Autonomous Payload Thermal Control
Alejandro D. Mousist
Deep Reinforcement Learning Thermal Control Autonomous Spacecraft Soft Actor Critic Algorithm Power Dissipation

March 8, 2023

Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint
Taisuke Kobayashi
Reinforcement Learning Soft Actor Critic Inequality Constraint Policy Entropy Soft Actor Critic Algorithm

February 2, 2023

MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks
Raffaele Galliera, Alessandro Morelli, Roberto Fronteddu, Niranjan Suri
Reinforcement Learning Real World Novel Reinforcement Learning Maximum Entropy Reinforcement Learning Congestion Control Soft Actor Critic Algorithm Efficient Protocol

January 10, 2023

Hint assisted reinforcement learning: an application in radio astronomy
Sarod Yatawatta
Reinforcement Learning Application Proficiency Simple Heuristic Natural Language Hint Model Development Radio Astronomy Soft Actor Critic Algorithm

December 5, 2022

FeSAC: Federated Learning-Based Soft Actor-Critic Traffic Offloading in Space-Air-Ground Integrated Network
Fengxiao Tang, Yilin Yang, Xin Yao, Ming Zhao, Nei Kato
Federated Prompt Cooperation Satellite Network Soft Actor Critic Algorithm Space Air Ground Integrated Network

September 20, 2022

A Deep Reinforcement Learning-Based Charging Scheduling Approach with Augmented Lagrangian for Electric Vehicle
Guibin. Chen, Xiaoying. Shi
Policy Gradient Electric Vehicle Deep Reinforcement Constrained Markov Decision Process Soft Actor Critic Algorithm Augmented Lagrangian

June 10, 2022

Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy
Hongzhi Hua, Kaigui Wu, Guixuan Wen
Multi Agent Action Space Multi Agent Deep Reinforcement Learning Maximum Entropy Soft Actor Critic Algorithm

April 21, 2022

Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations
Jing Wu, Ran Tao, Pan Zhao, Nicolas F. Martin, Naira Hovakimyan
Deep Reinforcement Learning Agricultural Domain Soft Actor Critic Algorithm Crop Simulation Network Management

Soft Actor Critic Algorithm

Papers

Augmented Lagrangian-Based Safe Reinforcement Learning Approach for Distribution System Volt/VAR Control

AI Olympics challenge with Evolutionary Soft Actor Critic

Sustainable Diffusion-based Incentive Mechanism for Generative AI-driven Digital Twins in Industrial Cyber-Physical Systems

Generalizing soft actor-critic algorithms to discrete action spaces

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

Autonomous Payload Thermal Control

Soft Actor-Critic Algorithm with Truly-satisfied Inequality Constraint

MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks

Hint assisted reinforcement learning: an application in radio astronomy

FeSAC: Federated Learning-Based Soft Actor-Critic Traffic Offloading in Space-Air-Ground Integrated Network

A Deep Reinforcement Learning-Based Charging Scheduling Approach with Augmented Lagrangian for Electric Vehicle

Deep Multi-Agent Reinforcement Learning with Hybrid Action Spaces based on Maximum Entropy

Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations