相关论文: Learning Robust Reasoning through Guided Adversari…

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

The emergence of compositional reasoning in large language models through reinforcement learning with verifiable rewards (RLVR) has been a key driver of recent empirical successes. Despite this progress, it remains unclear which…

Large Language Models (LLMs) have achieved remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR), yet still rely heavily on external supervision (e.g., curated labels). Adversarial learning, particularly through…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Robust Reinforcement Learning tries to make predictions more robust to changes in the dynamics or rewards of the system. This problem is particularly important when the dynamics and rewards of the environment are estimated from the data. In…

Solving math problems through verifiable languages such as Lean has significantly impacted both the mathematics and computer science communities. Current state-of-the-art models are often trained with expensive online Reinforcement Learning…

Adversarial examples have been shown to be the severe threat to deep neural networks (DNNs). One of the most effective adversarial defense methods is adversarial training (AT) through minimizing the adversarial risk $R_{adv}$, which…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer from an exploration dilemma: the sharply peaked initial…

No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error…

Reinforcement Learning (RL) is an effective tool for controller design but can struggle with issues of robustness, failing catastrophically when the underlying system dynamics are perturbed. The Robust RL formulation tackles this by adding…

Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in multiple domains, yet outcome-only scalar rewards are often sparse and uninformative, especially on failed samples, where they merely indicate…

Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settings. However, the success of adversarial optimization has…

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only final outcomes, which can lead to a failure mode where task…

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled even…

Reinforcement learning provides a powerful and general framework for decision making and control, but its application in practice is often hindered by the need for extensive feature and reward engineering. Deep reinforcement learning…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…