paper-with-me

홈 › Papers

RLBenchNet: The Right Network for the Right Reinforcement Learning Task

2025-05-21 · Ivan Smirnov, Shangding Gu

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL tasks, including Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), Mamba/Mamba-2, Transformer-XL, Gated Transformer-XL, and Gated Recurrent Unit (GRU). Through comprehensive evaluation across continuous control, discrete decision-making, and memory-based environments, we identify architecture-specific strengths and limitations. Our results reveal that: (1) MLPs excel in fully observable continuous control tasks, providing an optimal balance of performance and efficiency; (2) recurrent architectures like LSTM and GRU offer robust performance in partially observable environments with moderate memory requirements; (3) Mamba models achieve a 4.5x higher throughput compared to LSTM and a 3.9x increase over GRU, all while maintaining comparable performance; and (4) only Transformer-XL, Gated Transformer-XL, and Mamba-2 successfully solve the most challenging memory-intensive tasks, with Mamba-2 requiring 8x less memory than Transformer-XL. These findings provide insights for researchers and practitioners, enabling more informed architecture selection based on specific task characteristics and computational constraints. Code is available at: https://github.com/SafeRL-Lab/RLBenchNet

📄 PDF Abstract BibTeX arXiv:2505.15040

Code (1)

saferl-lab/rlbenchnet 공식 구현 pytorch

Tasks

continuous-controlContinuous ControlMambaReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Variational Dropout Variational Dropout is a regularization technique based on dropout, but uses a variational inference grounded approach. In…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

RLCP: A Reinforcement Learning-based Copyright Protection Method for Text-to-Image Diffusion Model

2024-08-29 · Zhuan Shi, Jing Yan, Xiaoli Tang, Lingjuan Lyu 외

The increasing sophistication of text-to-image generative models has led to complex challenges in defining and enforcing copyright infringement criteria and protection. Existing methods, such as watermarking and dataset …

Decision MakingDenoising

Copyright-Aware Incentive Scheme for Generative Art Models Using Hierarchical Reinforcement Learning

2024-10-26 · Zhuan Shi, Yifei Song, Xiaoli Tang, Lingjuan Lyu 외

Generative art using Diffusion models has achieved remarkable performance in image generation and text-to-image tasks. However, the increasing demand for training data in generative art raises significant concerns about …

Hierarchical Reinforcement LearningImage Generation

Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm

2021-03-17 · Lin Chen, Bruno Scherrer, Peter L. Bartlett

In this paper, we investigate the sample complexity of policy evaluation in infinite-horizon offline reinforcement learning (also known as the off-policy evaluation problem) with linear function approximation. We identif…

Off-policy evaluationReinforcement Learning (RL)

Challenges of Applying Deep Reinforcement Learning in Dynamic Dispatching

2020-11-09 · Hamed Khorasgani, HaiYan Wang, Chetan Gupta

Dynamic dispatching aims to smartly allocate the right resources to the right place at the right time. Dynamic dispatching is one of the core problems for operations optimization in the mining industry. Theoretically, de…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Graceful task adaptation with a bi-hemispheric RL agent

2024-07-16 · Grant Nicholas, Levin Kuhlmann, Gideon Kowadlo

In humans, responsibility for performing a task gradually shifts from the right hemisphere to the left. The Novelty-Routine Hypothesis (NRH) states that the right and left hemispheres are used to perform novel and routin…

Continual Learning