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

• URL: http://arxiv.org/abs/2505.23857v1
• Date: Thu, 29 May 2025 06:22:06 GMT
• Title: DATD3: Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient For Model Free Reinforcement Learning Under Output Feedback Control
• Abstract summary: Reinforcement learning in real-world applications often involves output-feedback settings, where the agent receives only partial state information.<n>We propose the Output-Feedback Markov Decision Process (OPMDP), which extends the standard MDP formulation to accommodate decision-making based on observation histories.<n>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.<n>Experiments on continuous control tasks demonstrate that DATD3 outperforms existing memory-based and recurrent baselines under both partial and full
• Score: 4.473337652382325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models [129.8880969196575]
  We present an empirical analysis of attention in Diffusion large language models (dLLMs)<n>We show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.<n>Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework.
  arXiv  Detail & Related papers  (2026-06-10T16:14:23Z)
• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• Improving Reconstruction of Representation Autoencoder [52.817427902597416]
  We propose LV-RAE, a representation autoencoder that augments semantic features with missing low-level information.<n>Our experiments demonstrate that LV-RAE significantly improves reconstruction fidelity while preserving the semantic abstraction.
  arXiv  Detail & Related papers  (2026-02-09T13:12:35Z)
• Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning [62.680551162054975]
  We introduce an end-to-end framework where LLMs learn to self-regulate the granularity of the reasoning steps through dynamic summarization.<n>We apply reinforcement learning to incentivize this capability further, uncovering a critical insight: the accuracy gap between the highly efficient Fold mode and the exhaustive Unfold mode progressively narrows.<n>Our Accordion-Thinker demonstrates that with learned self-compression, LLMs can tackle complex reasoning tasks with minimal dependency token overhead.
  arXiv  Detail & Related papers  (2026-02-03T08:34:20Z)
• Learning to Focus: Prioritizing Informative Histories with Structured Attention Mechanisms in Partially Observable Reinforcement Learning [9.233407096706744]
  We introduce structured inductive priors into the self-attention mechanism of the dynamics head.<n>Experiments on the Atari 100k benchmark show that most efficiency gains arise from the Gaussian prior.
  arXiv  Detail & Related papers  (2025-11-10T10:53:16Z)
• RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning [27.235259453535537]
  RationAnomaly is a novel framework that enhances log anomaly detection by synergizing Chain-of-Thought fine-tuning with reinforcement learning.<n>We have released the corresponding resources, including code and datasets.
  arXiv  Detail & Related papers  (2025-09-18T07:35:58Z)
• Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations [55.4735586739093]
  We introduce PDE, a new benchmark which enables systematic robustness evaluation.<n>PDE uses procedural generation to create 3D scenes that test robustness to various controlled perturbations.<n>Our analysis yields interesting findings on what perturbations are challenging for state-of-the-art depth models.
  arXiv  Detail & Related papers  (2025-07-01T17:33:48Z)
• SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields [11.872753517172555]
  We present SCENT, a novel framework for scalable and continuity-informed modeling learning.<n>SCENT unifies representation, reconstruction, and forecasting within a single architecture.<n>We validate SCENT through extensive simulations and real-world experiments, demonstrating state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-04-16T17:17:31Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.<n>We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• ACTRESS: Active Retraining for Semi-supervised Visual Grounding [52.08834188447851]
  A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. This approach is incompatible with current state-of-the-art visual grounding models, which follow the Transformer-based pipeline. Our paper proposes the ACTive REtraining approach for Semi-Supervised Visual Grounding, abbreviated as ACTRESS.
  arXiv  Detail & Related papers  (2024-07-03T16:33:31Z)
• Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL [57.202733701029594]
  We propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.<n>To address these challenges, we propose Decision Mamba, a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.<n>To mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization.
  arXiv  Detail & Related papers  (2024-06-08T10:12:00Z)
• DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery [71.6345505427213]
  DPMesh is an innovative framework for occluded human mesh recovery. It capitalizes on the profound diffusion prior about object structure and spatial relationships embedded in a pre-trained text-to-image diffusion model.
  arXiv  Detail & Related papers  (2024-04-01T18:59:13Z)
• Deep Common Feature Mining for Efficient Video Semantic Segmentation [25.851900402539467]
  We present Deep Common Feature Mining (DCFM) for video semantic segmentation.<n>DCFM explicitly decomposes features into two complementary components.<n>We incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency.
  arXiv  Detail & Related papers  (2024-03-05T06:17:59Z)
• IPED: An Implicit Perspective for Relational Triple Extraction based on Diffusion Model [7.894136732348917]
  Implicit Perspective for triple Extraction based on Diffusion model (IPED) We propose an Implicit Perspective for triple Extraction based on Diffusion model (IPED) Our solution adopts an implicit using block coverage to complete the tables, avoiding the limitations of explicit tagging methods.
  arXiv  Detail & Related papers  (2024-02-24T14:18:11Z)
• Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks [5.968716050740402]
  This paper focuses on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks. We design a Bias Exploiting (BE) mechanism to dynamically select the most advantageous estimation bias during training of the RL agent. Most State-of-the-art Deep RL algorithms can be equipped with the BE mechanism, without hindering performance or computational complexity.
  arXiv  Detail & Related papers  (2024-02-14T10:44:03Z)
• Sequential Action-Induced Invariant Representation for Reinforcement Learning [1.2046159151610263]
  How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a challenging problem in visual reinforcement learning. We propose a Sequential Action-induced invariant Representation (SAR) method, in which the encoder is optimized by an auxiliary learner to only preserve the components that follow the control signals of sequential actions.
  arXiv  Detail & Related papers  (2023-09-22T05:31:55Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)
• CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning [56.20123080771364]
  We develop a model-agnostic Contrastive-Curiosity-Driven Learning Framework (CCLF) for reinforcement learning. CCLF fully exploit sample importance and improve learning efficiency in a self-supervised manner. We evaluate this approach on the DeepMind Control Suite, Atari, and MiniGrid benchmarks.
  arXiv  Detail & Related papers  (2022-05-02T14:42:05Z)
• Gleo-Det: Deep Convolution Feature-Guided Detector with Local Entropy Optimization for Salient Points [5.955667705173262]
  We propose to achieve fine constraint based on the requirement of repeatability while coarse constraint with guidance of deep convolution features. With the guidance of convolution features, we define the cost function from both positive and negative sides.
  arXiv  Detail & Related papers  (2022-04-27T12:40:21Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Depth-Cooperated Trimodal Network for Video Salient Object Detection [13.727763221832532]
  We propose a depth-operated triOD network called DCTNet for video salient object detection (VS) To this end, we first generate depth from RGB frames, and then propose an approach to treat the three modalities unequally. We also introduce a refinement fusion module (RFM) to suppress noises in each modality and select useful information dynamically for further feature refinement.
  arXiv  Detail & Related papers  (2022-02-12T13:04:16Z)
• Unsupervised Visual Attention and Invariance for Reinforcement Learning [25.673868326662024]
  We develop an independent module to disperse interference factors irrelevant to the task, thereby providing "clean" observations for the vision-based reinforcement learning policy. All components are optimized in an unsupervised way, without manual annotation or access to environment internals. VAI empirically shows powerful generalization capabilities and significantly outperforms current state-of-the-art (SOTA) method by 15% to 49% in DeepMind Control suite benchmark.
  arXiv  Detail & Related papers  (2021-04-07T05:28:01Z)
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic [59.94347858883343]
  This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states.
  arXiv  Detail & Related papers  (2021-02-24T01:11:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.