相关论文: Context Representation via Action-Free Transformer…

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…

Autonomous navigation in unknown environments requires multi-scale spatial understanding that captures geometric details, topological connectivity, and global structure to support high-level decision making under partial observability.…

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and computer vision tasks. However, such a paradigm is still hindered by several challenges in Reinforcement…

Can we pre-train a generalist agent from a large amount of unlabeled offline trajectories such that it can be immediately adapted to any new downstream tasks in a zero-shot manner? In this work, we present a functional reward encoding (FRE)…

There is considerable interest in designing meta-reinforcement learning (meta-RL) algorithms, which enable autonomous agents to adapt new tasks from small amount of experience. In meta-RL, the specification (such as reward function) of…

This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple environments. Unlike traditional methods that require extensive…

Reinforcement Learning (RL) algorithms can solve challenging control problems directly from image observations, but they often require millions of environment interactions to do so. Recently, model-based RL algorithms have greatly improved…

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Many real-world domains are subject to a structured non-stationarity which affects the agent's goals and the environmental dynamics. Meta-reinforcement learning (RL) has been shown successful for training agents that quickly adapt to…

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills. This however often leads to low sample efficiency, requiring a large amount of interaction…

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain…

In-context reinforcement learning (ICRL) leverages the in-context learning capabilities of transformer models (TMs) to efficiently generalize to unseen sequential decision-making tasks without parameter updates. However, existing ICRL…

Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

In-context learning (ICL) allows Transformers to adapt to novel tasks without weight updates, yet the underlying algorithms remain poorly understood. We adopt a statistical decision-theoretic perspective by investigating simple binary…

Prior works have demonstrated that implicit representations trained only for reconstruction tasks typically generate encodings that are not useful for semantic tasks. In this work, we propose a method that contextualises the encodings of…

Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…