相关论文: PyTupli: A Scalable Infrastructure for Collaborati…

Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Automated Reinforcement Learning (AutoRL) is a relatively new area of research that is gaining increasing attention. The objective of AutoRL consists in easing the employment of Reinforcement Learning (RL) techniques for the broader public…

Machine learning is a general-purpose technology holding promises for many interdisciplinary research problems. However, significant barriers exist in crossing disciplinary boundaries when most machine learning tools are developed in…

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models…

As supercomputers continue to grow in scale and capabilities, it is becoming increasingly difficult to isolate processor and system level causes of performance degradation. Over the last several years, a significant number of performance…

Offline reinforcement learning (RL) offers a powerful paradigm for data-driven control. Compared to model-free approaches, offline model-based RL (MBRL) explicitly learns a world model from a static dataset and uses it as a surrogate…

Repository-level code completion benefits from retrieval-augmented generation (RAG). However, controlling cross-file evidence is difficult because chunk utility is often interaction-dependent: some snippets help only when paired with…

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occur due to inevitable model errors, degrading algorithm…

Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing…

Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the…

This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (RL), in-context, using foundation models. While the application of foundation models to RL has received considerable attention, most…

Offline reinforcement learning (RL) enables policy learning from static data but often suffers from poor coverage of the state-action space and distributional shift problems. This problem can be addressed by allowing limited online…

The idea of transfer in reinforcement learning (TRL) is intriguing: being able to transfer knowledge from one problem to another problem without learning everything from scratch. This promises quicker learning and learning more complex…

We consider the offline reinforcement learning problem, where the aim is to learn a decision making policy from logged data. Offline RL -- particularly when coupled with (value) function approximation to allow for generalization in large or…

Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains demonstrated by RL-based training methods like GRPO, a…

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current…

The offline reinforcement learning (RL) problem aims to learn an optimal policy from historical data collected by one or more behavioural policies (experts) by interacting with an environment. However, the individual experts may be…

Human beings, even small children, quickly become adept at figuring out how to use applications on their mobile devices. Learning to use a new app is often achieved via trial-and-error, accelerated by transfer of knowledge from past…