相关论文: Comprehensible Context-driven Text Game Playing

Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…

Long short-term memory (LSTM) is a kind of recurrent neural networks (RNN) for sequence and temporal dependency data modeling and its effectiveness has been extensively established. In this work, we propose a hybrid quantum-classical model…

Strategic reasoning enables agents to cooperate, communicate, and compete with other agents in diverse situations. Existing approaches to solving strategic games rely on extensive training, yielding strategies that do not generalize to new…

This paper proposes a deep neural network model for joint modeling Natural Language Understanding (NLU) and Dialogue Management (DM) in goal-driven dialogue systems. There are three parts in this model. A Long Short-Term Memory (LSTM) at…

The recent advances of deep learning in both computer vision (CV) and natural language processing (NLP) provide us a new way of understanding semantics, by which we can deal with more challenging tasks such as automatic description…

We design a simple reinforcement learning (RL) agent that implements an optimistic version of $Q$-learning and establish through regret analysis that this agent can operate with some level of competence in any environment. While we leverage…

Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed…

Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM…

Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions…

Modeling latent character states is crucial for consistent and engaging role-playing (RP) with large language models (LLMs). Yet, existing prompting-based approaches mainly capture surface actions, often failing to track the latent states…

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data.…

In this work, the trick-taking game Wizard with a separate bidding and playing phase is modeled by two interleaved partially observable Markov decision processes (POMDP). Deep Q-Networks (DQN) are used to empower self-improving agents,…

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables…

Recurrent neural networks (RNNs) have many advantages over more traditional system identification techniques. They may be applied to linear and nonlinear systems, and they require fewer modeling assumptions. However, these neural network…

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…

Text-based games present a unique challenge for autonomous agents to operate in natural language and handle enormous action spaces. In this paper, we propose the Contextual Action Language Model (CALM) to generate a compact set of action…

In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…

Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase. In this paper, we introduce a novel Convolutional Neural Network (CNN) that incorporates a Spatial Quad-Directional Long Short Term…

The Sentence-State LSTM (S-LSTM) is a powerful and high efficient graph recurrent network, which views words as nodes and performs layer-wise recurrent steps between them simultaneously. Despite its successes on text representations, the…

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of…