Cover Image

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yixian, Tang, Huaze, Wei, Changxu, Ding, Wenbo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Policy Newton Algorithm in Reproducing Kernel Hilbert Space
by: Zhang, Yixian, et al.
Published: (2025)

Decorrelated Soft Actor-Critic for Efficient Deep Reinforcement Learning
by: Küçükoğlu, Burcu, et al.
Published: (2025)

DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning
by: Ma, Xiaoteng, et al.
Published: (2020)

Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic
by: Vo, Thanh Vinh, et al.
Published: (2025)

Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
by: Yao, Wei, et al.
Published: (2025)

Revisiting Discrete Soft Actor-Critic
by: Zhou, Haibin, et al.
Published: (2022)

Average-Reward Soft Actor-Critic
by: Adamczyk, Jacob, et al.
Published: (2025)

Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC)
by: Mahran, Youssef, et al.
Published: (2025)

Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence
by: Zhu, Lingwei, et al.
Published: (2023)

DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
by: Cui, Mingxuan, et al.
Published: (2025)

Flow Actor-Critic for Offline Reinforcement Learning
by: Chae, Jongseong, et al.
Published: (2026)

Distributional Soft Actor-Critic with Diffusion Policy
by: Liu, Tong, et al.
Published: (2025)

Efficient $Q$-Learning and Actor-Critic Methods for Robust Average Reward Reinforcement Learning
by: Xu, Yang, et al.
Published: (2025)

Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning
by: Dong, Jinzong, et al.
Published: (2026)

SACn: Soft Actor-Critic with n-step Returns
by: Łyskawa, Jakub, et al.
Published: (2025)

Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift
by: Chen, Yanjun, et al.
Published: (2024)

Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning
by: Garcin, Samuel, et al.
Published: (2025)

Broad Critic Deep Actor Reinforcement Learning for Continuous Control
by: Thalagala, Shiron, et al.
Published: (2024)

Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives
by: Asad, Reza, et al.
Published: (2025)

Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
by: Yang, Tong, et al.
Published: (2023)

Quantum Advantage Actor-Critic for Reinforcement Learning
by: Kölle, Michael, et al.
Published: (2024)

Offline Actor-Critic Reinforcement Learning Scales to Large Models
by: Springenberg, Jost Tobias, et al.
Published: (2024)

Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios
by: Zhang, Feihong, et al.
Published: (2025)

Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning
by: Chen, Haohui, et al.
Published: (2024)

Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration
by: Bai, Qinxun, et al.
Published: (2025)

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control
by: Alzorgan, Hazim, et al.
Published: (2025)

Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control
by: Chen, Donghe, et al.
Published: (2025)

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning
by: Humayoo, Mahammad, et al.
Published: (2018)

Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning
by: Tao, Stone, et al.
Published: (2024)

Contraction Actor-Critic: Contraction Metric-Guided Reinforcement Learning for Robust Path Tracking
by: Cho, Minjae, et al.
Published: (2025)

Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution
by: Deproost, Senne, et al.
Published: (2024)

Optimal Stability of KL Divergence under Gaussian Perturbations
by: Pan, Jialu, et al.
Published: (2026)

Actor-Critics Can Achieve Optimal Sample Efficiency
by: Tan, Kevin, et al.
Published: (2025)

A Safety Modulator Actor-Critic Method in Model-Free Safe Reinforcement Learning and Application in UAV Hovering
by: Qi, Qihan, et al.
Published: (2024)

Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion
by: Sabatini, Gianluca, et al.
Published: (2026)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
by: Yuan, Rui, et al.
Published: (2026)

SAC-GLAM: Improving Online RL for LLM agents with Soft Actor-Critic and Hindsight Relabeling
by: Gaven, Loris, et al.
Published: (2024)

${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
by: Chen, Dingyang, et al.
Published: (2023)

AI Olympics challenge with Evolutionary Soft Actor Critic
by: Calì, Marco, et al.
Published: (2024)

Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences
by: Singh, Nikhil Kumar, et al.
Published: (2024)