Soft Actor Critic

Soft Actor-Critic (SAC) is a deep reinforcement learning algorithm aiming to learn robust and efficient policies by maximizing both expected reward and policy entropy. Current research focuses on improving SAC's sample efficiency, addressing safety constraints through methods like Lagrangian formulations and meta-gradient optimization, and extending its applicability to various domains including robotics, autonomous driving, and multi-agent systems. These advancements are significant because they enhance the practicality and reliability of reinforcement learning for real-world applications requiring safe and efficient decision-making in complex environments.

Papers

July 5, 2023

SACHA: Soft Actor-Critic with Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding
Qiushi Lin, Hang Ma
Multi Agent Reinforcement Learning Multi Agent Path Finding Soft Actor Critic Multi Agent Actor Critic

June 28, 2023

SARC: Soft Actor Retrospective Critic
Sukriti Verma, Ayush Chopra, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Piyush Gupta, Balaji Krishnamurthy
Policy Gradient Actor Critic Algorithm Gradient Estimation Soft Actor Critic Critic Model

May 19, 2023

Regularization of Soft Actor-Critic Algorithms with Automatic Temperature Adjustment
Ben You
Policy Evaluation Soft Actor Critic Policy Improvement Thermal Control

March 21, 2023

SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations
Khaled Nakhleh, Minahil Raza, Mack Tang, Matthew Andrews, Rinu Boney, Ilija Hadzic, Jeongran Lee, Atefeh Mohajeri, Karina Palyutina
Reinforcement Learning Collision Avoidance Real Robot Soft Actor Critic Polar Representation Local Planning

March 8, 2023

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

March 7, 2023

A Strategy-Oriented Bayesian Soft Actor-Critic Model
Qin Yang, Ramviyas Parasuraman
Dynamic Environment Markov Chain Monte Carlo Intelligent Agent Soft Actor Critic

March 1, 2023

The Point to Which Soft Actor-Critic Converges
Jianfei Ma
Exceptional Point Soft Actor Critic KL Divergence Soft Q Learning

January 31, 2023

Anti-Exploration by Random Network Distillation
Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov
Offline Reinforcement Learning Distribution Data Soft Actor Critic Sampling Free Random Network Distillation

December 20, 2022

Variational Quantum Soft Actor-Critic for Robotic Arm Control
Alberto Acuto, Paola Barillà, Ludovico Bozzolo, Matteo Conterno, Mattia Pavese, Antonio Policicchio
Deep Reinforcement Learning Quantum Computing Quantum Advantage Soft Actor Critic Variational Quantum

November 26, 2022

RL-Based Guidance in Outpatient Hysteroscopy Training: A Feasibility Study
Vladimir Poliakov, Kenan Niu, Emmanuel Vander Poorten, Dzmitry Tsetserukou
Human Guidance Soft Actor Critic Feasibility Study

October 20, 2022

RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
Yanfei Xiang, Xin Wang, Shu Hu, Bin Zhu, Xiaomeng Huang, Xi Wu, Siwei Lyu
Reinforcement Learning Deep Reinforcement Learning Action Space Robotic Manipulation Robotic Manipulator Soft Actor Critic

October 10, 2022

Reducing Action Space: Reference-Model-Assisted Deep Reinforcement Learning for Inverter-based Volt-Var Control
Qiong Liu, Ye Guo, Lirong Deng, Haotian Liu, Dongyu Li, Hongbin Sun
Deep Reinforcement Learning Action Space Soft Actor Critic DRL Algorithm Active Distribution Based Volt Var Control

September 27, 2022

Regularized Soft Actor-Critic for Behavior Transfer Learning
Mingxi Tan, Andong Tian, Ludovic Denoyer
Feature Imitation Constrained Markov Decision Process Maximum Entropy Soft Actor Critic Continuous Control Task Visual Force Imitation

September 21, 2022

Revisiting Discrete Soft Actor-Critic
Haibin Zhou, Zichuan Lin, Junyou Li, Qiang Fu, Wei Yang, Deheng Ye
Action Space Discrete Environment Soft Actor Critic Double Q Learning

April 22, 2022

TASAC: a twin-actor reinforcement learning framework with stochastic policy for batch process control
Tanuja Joshi, Hariprasad Kodamana, Harikumar Kandath, Niket Kaisare
Reinforcement Learning Soft Actor Critic Actor Critic Reinforcement Learning Stochastic Policy Policy Blending

April 20, 2022

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics
Yannis Flet-Berliac, Debabrota Basu
Reinforcement Learning Safe Reinforcement Learning Soft Actor Critic Maximum Entropy Reinforcement Learning Adversarial Game Risk Averse Reinforcement Learning

March 19, 2022

Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach
Jie Pan, Jingwei Huang, Gengdong Cheng, Yong Zeng
Reinforcement Learning Soft Actor Critic Mesh Generation Quadrilateral Mesh

February 9, 2022

Imitation Learning by State-Only Distribution Matching
Damian Boborzi, Christoph-Nikolas Straehle, Jens S. Buchner, Lars Mikelsons
Imitation Learning Policy Learning Soft Actor Critic Distribution Matching Adversarial Method Adversarial Imitation Learning

February 7, 2022

Soft Actor-Critic with Inhibitory Networks for Faster Retraining
Jaime S. Ide, Daria Mićović, Michael J. Guarino, Kevin Alcedo, David Rosenbluth, Adrian P. Pope
Deep Reinforcement Learning Faster Training Soft Actor Critic Retraining Method Auto Tuning Path Entropy Inhibitory Neuron

January 30, 2022

DearFSAC: An Approach to Optimizing Unreliable Federated Learning via Deep Reinforcement Learning
Chenghao Huang, Weilong Chen, Yuxi Chen, Shunji Yang, Yanru Zhang
Deep Reinforcement Learning Native Robustness Constructive Approach Soft Actor Critic Defect Sample Robustness Problem