While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g.

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g.

Small language models (SLMs) have shown promises for relation extraction (RE) when extracting RDF triples guided by SHACL shapes focused on common datatype properties. This paper investigates how SLMs handle both datatype and object properties for a complete RDF graph extraction. We show that the key bottleneck is related to long-tail distribution of rare properties. To solve this issue, we evaluate several strategies: stratified sampling, weighted loss, dataset scaling, and template-based synthetic data augmentation. We show that the best strategy to perform equally well over unbalanced target properties is to build a training set where the number of occurrences of each property exceeds a given threshold. To enable reproducibility, we publicly released our datasets, experimental results and code. Our findings offer practical guidance for training shape-aware SLMs and highlight promising directions for future work in semantic RE.

Reinforcement learning with human feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where models overfit to reward misspecification and drift from preferred behaviors observed during training. We introduce DRO-REBEL, a unified family of robust REBEL updates with type-$p$ Wasserstein, KL, and $χ^2$ ambiguity sets. Using Fenchel duality, each update reduces to a simple relative-reward regression, preserving scalability and avoiding PPO-style clipping or auxiliary value networks. Under standard linear-reward and log-linear policy classes with a data-coverage condition, we establish $O(n^{-1/4})$ estimation bounds with tighter constants than prior DRO-DPO approaches, and recover the minimax-optimal $O(n^{-1/2})$ rate via a localized Rademacher complexity analysis. The same analysis closes the gap for Wasserstein-DPO and KL-DPO, showing both also attain optimal parametric rates. We derive practical SGD algorithms for all three divergences: gradient regularization (Wasserstein), importance weighting (KL), and a fast 1-D dual solve ($χ^2$). Experiments on Emotion Alignment, the large-scale ArmoRM multi-objective benchmark, and HH-Alignment demonstrate strong worst-case robustness across unseen preference mixtures, model sizes, and data scales, with $χ^2$-REBEL showing consistently strong empirical performance. A controlled radius--coverage study validates a no-free-lunch trade-off: radii shrinking faster than empirical divergence concentration rates achieve minimax-optimal parametric rates but forfeit coverage, while coverage-guaranteeing radii incur $O(n^{-1/4})$ rates.

According to the papre, ReBeL is a novel method to deal with two-player zero-sum imperfect-information games. And it may be able to be used to solve other inperfect-information problem. And the domain of this paper, multi-agents RL in imperfect-information, has high relevance to NIPS. 6. The experiment compared the module with human player, which is a strong evidence of the exploitability of ReBeL.

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative reward between two completions to a prompt in terms of the policy, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature.

AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-written strategy. This paper investigates how well AI systems can generate and act on strategies for subverting control protocols whilst operating without private memory. Usually, decision-makers only need the ability to generate optimal plans. However, to subvert a protocol, an AI system must be able to reliably generate optimal plans in each context; coordinate plans with other instances of itself without communicating; and take actions with well-calibrated probabilities. We develop evaluations for a model's ability to generate subversion strategies and develop affordance experiments that help isolate component capabilities. Our initial evaluations with Claude-3.5-sonnet highlight reasons why statelessly strategizing to subvert control protocols might be hard. We hope that our work can serve as a starting point for evaluations aimed at assessing whether a model is capable of strategizing to subvert control protocols.