相关论文: GRPOformer: Advancing Hyperparameter Optimization …

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

Group Relative Policy Optimization (GRPO), recently introduced by DeepSeek, is a critic-free reinforcement learning algorithm for fine-tuning large language models. GRPO replaces the value function in Proximal Policy Optimization (PPO) with…

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of learned reward models. Building on this paradigm, Group…

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Legged locomotion in unstructured environments demands not only high-performance control policies but also formal guarantees to ensure robustness under perturbations. Control methods often require carefully designed reference trajectories,…

We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework.…

Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often makes it difficult to achieve good results in practice.…

Training large language models (LLMs) as interactive agents for controlling graphical user interfaces (GUIs) presents a unique challenge to optimize long-horizon action sequences with multimodal feedback from complex environments. While…

In this project we demonstrate the effectiveness of the transformer encoder as a viable architecture for policies in variable action environments. Using it, we train an agent using Proximal Policy Optimisation (PPO) on multiple maps against…

Group Relative Policy Optimization (GRPO) has emerged as a popular algorithm for reinforcement learning with large language models (LLMs). However, upon analyzing its clipping mechanism, we argue that it is suboptimal in certain scenarios.…

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constraints. In this paper, we demonstrate that strong duality does…

We introduce Hierarchical Transformers for Meta-Reinforcement Learning (HTrMRL), a powerful online meta-reinforcement learning approach. HTrMRL aims to address the challenge of enabling reinforcement learning agents to perform effectively…

Group Relative Policy Optimization (GRPO) enhances policy learning by computing gradients from relative comparisons among candidate outputs that share a common input prefix. Despite its effectiveness, GRPO introduces substantial…

Group-based reinforcement learning algorithms such as Group Reward Policy Optimization (GRPO) have proven effective for fine-tuning large language models (LLMs) with human feedback. However, generating and storing multiple responses per…

Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment signals and remain…

Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer…

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response…

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Recent advances in GPU-based parallel simulation have enabled practitioners to collect large amounts of data and train complex control policies using deep reinforcement learning (RL), on commodity GPUs. However, such successes for RL in…

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize…