相关论文: Stabilizing Off-Policy Training for Long-Horizon L…

Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases…

Existing predictive maintenance (PdM) methods typically focus solely on whether to replace system components without considering the costs incurred by inspection. However, a well-considered approach should be able to minimize Remaining…

Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing…

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain…

In many real-world scenarios, Reinforcement Learning (RL) algorithms are trained on data with dynamics shift, i.e., with different underlying environment dynamics. A majority of current methods address such issue by training context…

State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. In this paper, we…

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.…

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees. However, deploying existing constrained RL algorithms in continuous control tasks with general hard constraints…

Zeroth-order (ZO, also known as derivative-free) methods, which estimate the gradient only by two function evaluations, have attracted much attention recently because of its broad applications in machine learning community. The two function…

Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimization. Despite the empirical success of GRPO-style methods,…

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external…

Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However, there is a significant disconnect between the underlying…

Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative…

This paper presents a deep reinforcement learning (DRL) framework for dynamic portfolio optimization under market uncertainty and risk. The proposed model integrates a Sharpe ratio-based reward function with direct risk control mechanisms,…

Plateaus, where an agent's performance stagnates at a suboptimal level, are a common problem in deep on-policy RL. Focusing on PPO due to its widespread adoption, we show that plateaus in certain regimes arise not because of known…

Multi-objective reinforcement learning (MORL) is essential for addressing the intricacies of real-world RL problems, which often require trade-offs between multiple utility functions. However, MORL is challenging due to unstable learning…