Related papers: Trust, Don't Trust, or Flip: Robust Preference-Bas…

Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either overly destructive or too conservative. We propose…

Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on…

Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be…

Bias is a common problem inherent in recommender systems, which is entangled with users' preferences and poses a great challenge to unbiased learning. For debiasing tasks, the doubly robust (DR) method and its variants show superior…

Many sequential decision-making tasks involve optimizing multiple conflicting objectives, requiring policies that adapt to different user preferences. In multi-objective reinforcement learning (MORL), one widely studied approach} addresses…

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hacking, such as quality degradation, over-stylization, or…

Learning-to-rank (LTR) algorithms are ubiquitous and necessary to explore the extensive catalogs of media providers. To avoid the user examining all the results, its preferences are used to provide a subset of relatively small size. The…

In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is…

The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems. Among existing solutions, automatic ULTR algorithms that jointly learn user bias models (i.e., propensity models)…

For effective real-world deployment, robots should adapt to human preferences, such as balancing distance, time, and safety in delivery routing. Active preference learning (APL) learns human reward functions by presenting trajectories for…

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar…

Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For…

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the…

Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-off (BNT): improving performance on unseen (new) classes often degrades accuracy on known (base) classes. Addressing how to boost…

In this paper, we consider combinatorial reinforcement learning with preference feedback, where a learning agent sequentially offers an action--an assortment of multiple items to--a user, whose preference feedback follows a multinomial…

A variety of autonomous navigation algorithms exist that allow robots to move around in a safe and fast manner. However, many of these algorithms require parameter re-tuning when facing new environments. In this paper, we propose PTDRL, a…

Ensuring reliability in adversarial settings necessitates treating privacy as a foundational component of data-driven systems. While differential privacy and cryptographic protocols offer strong guarantees, existing schemes rely on a fixed…

Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end…