Related papers: How's it going? Reinforcement learning in language…

Reinforcement learning (RL) requires either manually specifying a reward function, which is often infeasible, or learning a reward model from a large amount of human feedback, which is often very expensive. We study a more sample-efficient…

While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural…

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

For adversarial imitation learning algorithms (AILs), no true rewards are obtained from the environment for learning the strategy. However, the pseudo rewards based on the output of the discriminator are still required. Given the implicit…

The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are able to communicate their competencies, we present a method of…

In sequential decision-making problems involving sensitive attributes like race and gender, reinforcement learning (RL) agents must carefully consider long-term fairness while maximizing returns. Recent works have proposed many different…

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilities. Although many…

This dissertation establishes the contexture theory to mathematically characterize the mechanism of representation learning, or pretraining. Despite the remarkable empirical success of foundation models, it is not very clear what…

Reinforcement learning (RL) is increasingly used to post-train medical Vision-Language Models (VLMs), yet it remains unclear whether RL improves medical visual reasoning or mainly sharpens behaviors already induced by supervised fine-tuning…

Fear is a critical brain function that enables us to learn to avoid danger via reinforcement learning (RL). While many researchers have argued that fear has evolved to escape predators, how varying predatory pressures have shaped fear and…

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…

Regression models usually tend to recover a noisy signal in the form of a combination of regressors, also called features in machine learning, themselves being the result of a learning process.The alignment of the prior covariance feature…

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's…

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

The alignment of large language models (LLMs) is crucial for generating helpful and harmless content. Existing approaches leverage preference-based human feedback data to learn the reward function and align the LLM with the feedback data.…

Reinforcement learning has emerged as a powerful paradigm for post-training large language models (LLMs) to improve reasoning. Approaches like Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable…

Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems. A common practice is to apply RL on a neural sequence-to-sequence (seq2seq) framework with the action space…

Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors),…

Recent advances such as DeepSeek R1-Zero highlight the effectiveness of incentive training, a reinforcement learning paradigm that computes rewards solely based on the final answer part of a language model's output, thereby encouraging the…