相关论文: PCGRL+: Scaling, Control and Generalization in Rei…

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's…

Procedural content generation uses algorithmic techniques to create large amounts of new content for games at much lower production costs. In newer approaches, procedural content generation utilizes machine learning. However, these methods…

Reinforcement learning (RL) has shown strong promise for LLM-based machine translation, with recent methods such as GRPO demonstrating notable gains; nevertheless, translation-oriented RL remains challenged by noisy learning signals arising…

A major challenge in the Deep RL (DRL) community is to train agents able to generalize over unseen situations, which is often approached by training them on a diversity of tasks (or environments). A powerful method to foster diversity is to…

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb…

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…

Hierarchical reinforcement learning (HRL) learns to make decisions on multiple levels of temporal abstraction. A key challenge in HRL is that the low-level policy changes over time, making it difficult for the high-level policy to generate…

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…

Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental…

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to…

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…

Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game researches. Among a variety of PCG techniques, search-based approaches overwhelmingly dominate PCG development at…

It remains a significant challenge to train generally capable agents with reinforcement learning (RL). A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames…

Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and rely on large language…

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging…

When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy…

Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…