paper-with-me

Papers

DATD3: Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient For Model Free Reinforcement Learning Under Output Feedback Control

2025-05-29 · Wuhao Wang, Zhiyong Chen

Reinforcement learning in real-world applications often involves output-feedback settings, where the agent receives only partial state information. To address this challenge, we propose the Output-Feedback Markov Decision Process (OPMDP), which extends the standard MDP formulation to accommodate decision-making based on observation histories. Building on this framework, we introduce Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient (DATD3), a novel actor-critic algorithm that employs depthwise separable convolution and multi-head attention to encode historical observations. DATD3 maintains policy expressiveness while avoiding the instability of recurrent models. Extensive experiments on continuous control tasks demonstrate that DATD3 outperforms existing memory-based and recurrent baselines under both partial and full observability.

📄 PDF Abstract BibTeX arXiv:2505.23857

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlDecision Making

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention 설명 없음
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…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
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 $x$…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Multi-Head Attention 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution

Similar Papers 제목 키워드 기반

Twin actor twin delayed deep deterministic policy gradient (TATD3) learning for batch process control

2021-02-25 · Tanuja Joshi, Shikhar Makker, Hariprasad Kodamana, Harikumar Kandath

Control of batch processes is a difficult task due to their complex nonlinear dynamics and unsteady-state operating conditions within batch and batch-to-batch. It is expected that some of these challenges can be addresse…

continuous-controlContinuous ControlReinforcement Learning (RL)

When Do Drivers Concentrate? Attention-based Driver Behavior Modeling With Deep Reinforcement Learning

2020-02-26 · Xingbo Fu, Feng Gao, Jiang Wu

Driver distraction a significant risk to driving safety. Apart from spatial domain, research on temporal inattention is also necessary. This paper aims to figure out the pattern of drivers' temporal attention allocation.…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3)

2025-12-15 · Zeyad Gamal, Youssef Mahran, Ayman El-Badawy arxiv

This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specific pitch and azimuth angles and tracking a given trajectory. The complex dynam…

Reinforcement Learning

Adaptive Temporal Difference Learning with Linear Function Approximation

2020-02-20 · Tao Sun, Han shen, Tianyi Chen, Dongsheng Li

This paper revisits the temporal difference (TD) learning algorithm for the policy evaluation tasks in reinforcement learning. Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of step…

OpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)

TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade Execution

2026-06-07 · Ilia Zaznov, Atta Badii, Julian Kunkel, Alfonso Dufour arxiv

This study addresses the optimal execution of large stock sell programs by introducing TT-DAC-PS (Twin-Target Deterministic Actor-Critic with Policy Smoothing), a deterministic actor-critic architecture that combines twi…