Langevin Soft Actor-critic: Efficient Exploration Through Uncertainty-driven Critic Learning

Abstract

Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a novel model-free RL algorithm, Langevin Soft Actor Critic (LSAC), which prioritizes enhancing critic learning through uncertainty estimation over policy optimization. LSAC employs three key innovations: approximate Thompson sampling through distributional Langevin Monte Carlo (LMC) based \(Q\) updates, parallel tempering for exploring multiple modes of the posterior of the \(Q\) function, and diffusion synthesized state-action samples regularized with \(Q\) action gradients. Our extensive experiments demonstrate that LSAC outperforms or matches the performance of mainstream model-free RL algorithms for continuous control tasks. Notably, LSAC marks the first successful application of an LMC bas

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyishfaq2025langevin

Related papers

• Wasserstein Actor-critic: Directed Exploration Via Optimism For Continuous-actions Control (2023)2.26
• Wasserstein Barycenter Soft Actor-critic (2025)0.00
• DR-SAC: Distributionally Robust Soft Actor-critic For Reinforcement Learning Under Uncertainty (2025)0.00
• Soft Actor-critic: Off-policy Maximum Entropy Deep Reinforcement Learning With A Stochastic Actor (2018)0.00
• Bounded Exploration With World Model Uncertainty In Soft Actor-critic Reinforcement Learning Algorithm (2024)0.00
• Simultaneous Double Q-learning With Conservative Advantage Learning For Actor-critic Methods (2022)0.00
• DSAC: Distributional Soft Actor-critic For Risk-sensitive Reinforcement Learning (2020)7.81
• Distributional Soft Actor-critic: Off-policy Reinforcement Learning For Addressing Value Estimation Errors (2020)17.77