paper-with-me

Papers

Langevin DQN

2020-02-17 · Vikranth Dwaracherla, Benjamin Van Roy

Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count distributions. An open question is whether deep exploration can be achieved by an incremental reinforcement learning algorithm that tracks a single point estimate, without additional complexity required to account for epistemic uncertainty. We answer this question in the affirmative. In particular, we develop Langevin DQN, a variation of DQN that differs only in perturbing parameter updates with Gaussian noise and demonstrate through a computational study that the presented algorithm achieves deep exploration. We also offer some intuition to how Langevin DQN achieves deep exploration. In addition, we present a modification of the Langevin DQN algorithm to improve the computational efficiency.

📄 PDF Abstract BibTeX arXiv:2002.07282

Code (2)

vik0/LangevinDQN 공식 구현 tf
opent03/LangevinDQN-torch pytorch

Tasks

Computational EfficiencyOpen-Ended Question Answeringreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Langevin algorithms for very deep Neural Networks with application to image classification

2022-12-27 · Pierre Bras

Training a very deep neural network is a challenging task, as the deeper a neural network is, the more non-linear it is. We compare the performances of various preconditioned Langevin algorithms with their non-Langevin c…

image-classificationImage Classification

Subspace Langevin Monte Carlo

2024-12-18 · Tyler Maunu, Jiayi Yao

Sampling from high-dimensional distributions has wide applications in data science and machine learning but poses significant computational challenges. We introduce Subspace Langevin Monte Carlo (SLMC), a novel and effic…

Computational Efficiency

Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis

2025-03-24 · Nian Yao, Pervez Ali, Xihua Tao, Lingjiong Zhu

Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based…

Regime-Switching Langevin Monte Carlo Algorithms

2025-08-31 · Xiaoyu Wang, Yingli Wang, Lingjiong Zhu arxiv

Langevin Monte Carlo (LMC) algorithms are popular Markov Chain Monte Carlo (MCMC) methods to sample a target probability distribution, which arises in many applications in machine learning. Inspired by regime-switching s…

On the Mode-Seeking Properties of Langevin Dynamics

2024-06-04 · Xiwei Cheng, Kexin Fu, Farzan Farnia

The Langevin Dynamics framework, which aims to generate samples from the score function of a probability distribution, is widely used for analyzing and interpreting score-based generative modeling. While the convergence …