Related papers: Filtering Learning Histories Enhances In-Context R…

Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted with training and test examples, without any parameter…

Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at…

We introduce Hierarchical Transformers for Meta-Reinforcement Learning (HTrMRL), a powerful online meta-reinforcement learning approach. HTrMRL aims to address the challenge of enabling reinforcement learning agents to perform effectively…

In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously…

Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise labels and thus fails to adequately capture relative preference relations among…

Transformers have shown a remarkable ability for in-context learning (ICL), making predictions based on contextual examples. However, while theoretical analyses have explored this prediction capability, the nature of the inferred context…

Offline reinforcement learning (RL) algorithms can learn better decision-making compared to behavior policies by stitching the suboptimal trajectories to derive more optimal ones. Meanwhile, Decision Transformer (DT) abstracts the RL as…

A Reinforcement Learning (RL) system depends on a set of initial conditions (hyperparameters) that affect the system's performance. However, defining a good choice of hyperparameters is a challenging problem. Hyperparameter tuning often…

Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also…

What if artificial intelligence could not only solve problems for which it was trained but also learn to teach itself to solve new problems (i.e., meta-learn)? In this study, we demonstrate that a pre-trained transformer fine-tuned with…

Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trained to solve. In this paper, we study the in-context…

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data…

Pretrained Transformers demonstrate remarkable in-context learning (ICL) capabilities, enabling them to adapt to new tasks from demonstrations without parameter updates. However, theoretical studies often rely on simplified architectures…

Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity…

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, adapting to new tasks by simply conditioning on demonstrations without parameter updates. Compelling empirical and theoretical evidence suggests that ICL, as…

The remarkable performance of Large Language Models (LLMs) can be enhanced with test-time computation, which relies on external tools and even other deep learning models. However, existing approaches for integrating non-text modality…

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

While large language models based on the transformer architecture have demonstrated remarkable in-context learning (ICL) capabilities, understandings of such capabilities are still in an early stage, where existing theory and mechanistic…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned reward models makes it vulnerable to mis-specification and reward hacking. Preference-based…

The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…