Related papers: ISOPO: Proximal policy gradients without pi-old
Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…
Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…
Proximal Policy Optimization algorithm employing a clipped surrogate objective (PPO-Clip) is a prominent exemplar of the policy optimization methods. However, despite its remarkable empirical success, PPO-Clip lacks theoretical…
Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…
We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping on the importance-sampling (IS) weight. We study RL methods with sequence-level IS and identify…
Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains…
Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at…
Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving…
Reinforcement learning has emerged as a dominant technique for fine-tuning the behavior of large language models, with policy optimization (PO) algorithms such as GRPO, DAPO, and Dr. GRPO emerging in rapid succession to advance…
Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…
Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models with human preferences. However, policy gradient methods such as PPO suffer from high variance gradient estimates,…
We cast policy gradient methods as the repeated application of two operators: a policy improvement operator $\mathcal{I}$, which maps any policy $\pi$ to a better one $\mathcal{I}\pi$, and a projection operator $\mathcal{P}$, which finds…
Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…
Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single…
Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), as the widely employed policy based reinforcement learning (RL) methods, are prone to converge to a sub-optimal solution as they limit the policy representation…
Wasserstein Policy Optimization (WPO) is a recently proposed reinforcement learning algorithm that leverages Wasserstein gradient flows to optimize stochastic policies in continuous action spaces. Despite its empirical success, the…
In RL, given a prompt, we sample a group of completions from a model and score them. Two questions follow: which completions should gain probability mass, and how should the parameters move to realize that change? Standard policy-gradient…
Proximal Policy Optimization (PPO) has been broadly applied to robotics learning, showcasing stable training performance. However, the fixed clipping bound setting may limit the performance of PPO. Specifically, there is no theoretical…
Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning these policies via RL remains challenging due to instability…
Decoupled PPO has been a successful reinforcement learning (RL) algorithm to deal with the high data staleness under the asynchronous RL setting. Decoupled loss used in decoupled PPO improves coupled-loss style of algorithms' (e.g.,…