Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv:2608. 06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as mathematical reasoning and code execution.
arXiv:2608. 07335v1 Announce Type: cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms.
arXiv:2607. 11953v3 Announce Type: replace Abstract: Does a reinforcement-learning agent that earns high reward actually learn its task's hidden state, or only a shortcut that correlates with reward?
arXiv:2608. 07118v1 Announce Type: new Abstract: Credit assignment in multi-turn agent reinforcement learning operates at two levels: assigning trajectory-level credit to actions and distributing each action's credit across its tokens.
arXiv:2608. 06792v1 Announce Type: cross Abstract: Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior.
arXiv:2608. 06381v1 Announce Type: cross Abstract: Explainable AI (XAI) has shown promise for human-agent collaboration, yet results rely on hand-crafted policies in custom environments, limiting generalizability to state-of-the-art teaming research.
arXiv:2601. 19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.
arXiv:2608. 07437v1 Announce Type: new Abstract: Reliable hypothesis testing is the foundation of many empirical scientific claims.
arXiv:2608. 06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.
arXiv:2608. 07086v1 Announce Type: cross Abstract: Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many tightly coupled factors.
arXiv:2509. 06296v2 Announce Type: replace-cross Abstract: Traditional on-policy reinforcement learning (RL) controllers for quadrupedal locomotion often suffer from low data efficiency, requiring millions of interactions with simulated environments to achieve stable control.
arXiv:2608. 06668v1 Announce Type: new Abstract: As an important component of the supply chain industry, transportation has experienced rapid development in the past decade with the assistance of digital platforms and intelligent algorithms.
arXiv:2608. 06559v1 Announce Type: new Abstract: Contextual bandits offer a natural framework for sample-efficient personalization, but practical deployment remains difficult under sparse, biased interaction data, unreliable uncertainty estimates, and severe cold starts.
arXiv:2608. 07301v1 Announce Type: new Abstract: We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone.
arXiv:2608. 07151v1 Announce Type: cross Abstract: Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness.
arXiv:2608. 07139v1 Announce Type: new Abstract: Uncertainty quantification is essential when deploying machine learning models in safety-critical applications.
arXiv:2608. 07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy.
arXiv:2608. 07148v1 Announce Type: new Abstract: Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity, reflex speed response with long horizon effects, delayed and diffuse outcomes, and dynamics that resist explicit modeling.
arXiv:2608. 06474v1 Announce Type: new Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap.
arXiv:2604. 00310v2 Announce Type: replace-cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.