Related papers: Diversity or Precision? A Deep Dive into Next Toke…

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy…

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training method for improving the reasoning abilities of Large Language Models (LLMs). However, existing methods mainly apply uniform optimization…

Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, leading…

Model-free continuous control for robot navigation tasks using Deep Reinforcement Learning (DRL) that relies on noisy policies for exploration is sensitive to the density of rewards. In practice, robots are usually deployed in cluttered…

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure reasoning models into sophisticated…

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms.…

Exploration is essential for reinforcement learning (RL). To face the challenges of exploration, we consider a reward-free RL framework that completely separates exploration from exploitation and brings new challenges for exploration…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. This differs from human decision-making, where gains and losses are valued differently and…

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has broadened exploration and enabled precise multi-objective…

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…

In reinforcement learning (RL), the consideration of multivariate reward signals has led to fundamental advancements in multi-objective decision-making, transfer learning, and representation learning. This work introduces the first…

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…