相关论文: Temporally Extended Successor Representations

In end-to-end automatic speech recognition (ASR), a model is expected to implicitly learn representations suitable for recognizing a word-level sequence. However, the huge abstraction gap between input acoustic signals and output linguistic…

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…

This paper presents a reinforcement learning framework that incorporates a Contextual Reward Machine for task-oriented grasping. The Contextual Reward Machine reduces task complexity by decomposing grasping tasks into manageable sub-tasks.…

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We…

Reward specification plays a central role in reinforcement learning (RL), guiding the agent's behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However,…

Estimating the covariance structure of multivariate time series is a fundamental problem with a wide-range of real-world applications -- from financial modeling to fMRI analysis. Despite significant recent advances, current state-of-the-art…

Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction…

We consider the problem of reward learning for temporally extended tasks. For reward learning, inverse reinforcement learning (IRL) is a widely used paradigm. Given a Markov decision process (MDP) and a set of demonstrations for a task, IRL…

We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is structured around CNN-based representation layers, each…

Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming…

Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously…

Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a…

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future outcomes. In this paper, we consider the problem…

Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…

Reinforcement Learning (RL) can be considered as a sequence modeling task: given a sequence of past state-action-reward experiences, an agent predicts a sequence of next actions. In this work, we propose State-Action-Reward Transformer…

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive…

Representation learning models for graphs are a successful family of techniques that project nodes into feature spaces that can be exploited by other machine learning algorithms. Since many real-world networks are inherently dynamic, with…

In self-supervised spatio-temporal representation learning, the temporal resolution and long-short term characteristics are not yet fully explored, which limits representation capabilities of learned models. In this paper, we propose a…

Model-free reinforcement learning (RL) is a powerful approach for learning control policies directly from high-dimensional state and observation. However, it tends to be data-inefficient, which is especially costly in robotic learning…