Related papers: Strategic Attentive Writer for Learning Macro-Acti…

We investigate the integration of a planning mechanism into sequence-to-sequence models using attention. We develop a model which can plan ahead in the future when it computes its alignments between input and output sequences, constructing…

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential…

We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation. We develop a model that plans ahead when it computes alignments between the…

Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks…

We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct…

Recent advancements in robot navigation, particularly with end-to-end learning approaches such as reinforcement learning (RL), have demonstrated strong performance. However, successful navigation still depends on two key capabilities:…

This paper describes a systematic approach towards building a new family of neural networks based on a delay-loop version of a reservoir neural network. The resulting architecture, called Scaled-Time-Attention Robust Edge (STARE) network,…

Deep Recurrent Neural Network architectures, though remarkably capable at modeling sequences, lack an intuitive high-level spatio-temporal structure. That is while many problems in computer vision inherently have an underlying high-level…

Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which weakens both exploration and credit…

We introduce Active Tuning, a novel paradigm for optimizing the internal dynamics of recurrent neural networks (RNNs) on the fly. In contrast to the conventional sequence-to-sequence mapping scheme, Active Tuning decouples the RNN's…

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent…

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing…

Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD)…

Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to…

While deep reinforcement learning excels at solving tasks where large amounts of data can be collected through virtually unlimited interaction with the environment, learning from limited interaction remains a key challenge. We posit that an…

Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources.…

We propose a novel deep structured learning framework for event temporal relation extraction. The model consists of 1) a recurrent neural network (RNN) to learn scoring functions for pair-wise relations, and 2) a structured support vector…

Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…

In real-time strategy (RTS) game artificial intelligence research, various multi-agent deep reinforcement learning (MADRL) algorithms are widely and actively used nowadays. Most of the research is based on StarCraft II environment because…

A commonly used technique for managing AI complexity in real-time strategy (RTS) games is to use action and/or state abstractions. High-level abstractions can often lead to good strategic decision making, but tactical decision quality may…