相关论文: P-TA: Using Proximal Policy Optimization to Enhanc…

The generation of data is a common approach to improve the performance of machine learning tasks, among which is the training of models for classification. In this paper, we present TAGAL, a collection of methods able to generate synthetic…

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from…

Tabular prediction traditionally relies on gradient-boosted decision trees and deep learning models, which excel in specific tasks but lack interpretability and transferability. Reasoning large language models (LLMs) promise cross-task…

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a…

A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation…

Aviation training is a core link in ensuring flight safety, improving industry efficiency and promoting sustainable development. It not only involves flight simulation but also requires the learning of a great deal of professional aviation…

In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial…

Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via…

Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans…

Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known as language confusion. Prior mitigation approaches based on…

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, we observe that in a continuous action space, PPO can prematurely shrink the exploration variance, which leads to slow progress…

Text-to-audio (T2A) generation has advanced considerably in recent years, yet existing methods continue to face challenges in accurately rendering complex text prompts, particularly those involving intricate audio effects, and achieving…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant…

Proximal Policy Optimization (PPO) is commonly used in Reinforcement Learning from Human Feedback to align large language models (LLMs) with downstream tasks. This paper investigates the feasibility of using PPO for direct reinforcement…

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Proximal Policy Optimization (PPO) is a widely used reinforcement learning algorithm that heavily relies on accurate advantage estimates for stable and efficient training. However, raw advantage signals can exhibit significant variance,…