相关论文: Sparse-RL: Breaking the Memory Wall in LLM Reinfor…

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse…

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Reinforcement learning (RL) for large language models is an energy-intensive endeavor: training can be unstable, and the policy may gradually drift away from its pretrained weights. We present \emph{RLEP}\, -- \,Reinforcement Learning with…

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for…

Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire…

This thesis rigorously studies fundamental reinforcement learning (RL) methods in modern practical considerations, including robust RL, distributional RL, and offline RL with neural function approximation. The thesis first prepares the…

Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like…

Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…

This article proposes a sparse computation-based method for optimizing neural networks for reinforcement learning (RL) tasks. This method combines two ideas: neural network pruning and taking into account input data correlations; it makes…

In this work, we address the problem of determining reliable policies in reinforcement learning (RL), with a focus on optimization under uncertainty and the need for performance guarantees. While classical RL algorithms aim at maximizing…

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…

While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance (Pass@k) despite improvements in single-attempt accuracy…

Large language models (LLMs) exhibit impressive capabilities in generation tasks but are prone to producing harmful, misleading, or biased content, posing significant ethical and safety concerns. To mitigate such risks, representation…

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…

Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervised loss functions for stably training deep reinforcement…