Related papers: Online Experiential Learning for Language Models

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical…

The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI…

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate…

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents:…

We present a unified framework for Batch Online Learning (OL) for Click Prediction in Search Advertisement. Machine Learning models once deployed, show non-trivial accuracy and calibration degradation over time due to model staleness. It is…

Transfer learning in Reinforcement Learning (RL) has been widely studied to overcome training issues of Deep-RL, i.e., exploration cost, data availability and convergence time, by introducing a way to enhance training phase with external…

This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD). Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state…

We study learning control in an online reset-free lifelong learning scenario, where mistakes can compound catastrophically into the future and the underlying dynamics of the environment may change. Traditional model-free policy learning…

In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline. Online methods explore the environment at significant time cost, and offline methods efficiently obtain reward signals by…

Open Information Extraction (OIE) aims to extract objective structured knowledge from natural texts, which has attracted growing attention to build dedicated models with human experience. As the large language models (LLMs) have exhibited…

This work introduces Transformer-based Off-Policy Episodic Reinforcement Learning (TOP-ERL), a novel algorithm that enables off-policy updates in the ERL framework. In ERL, policies predict entire action trajectories over multiple time…

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative…

Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an offline dataset and subsequently deploying them in an online…

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL),…

We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA…

This paper presents an evolutionary framework for the training of large language models(LLM). The models are divided into several experts(sub-networks), which have the same structure but different parameter values. Only one expert is…