Related papers: Rollout Pass-Rate Control: Steering Binary-Reward …
We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with only 180 training queries, a $2.7\times$ improvement over…
Offline reinforcement learning (RL) methods aim to learn optimal policies with access only to trajectories in a fixed dataset. Policy constraint methods formulate policy learning as an optimization problem that balances maximizing reward…
Training tool-calling agents with reinforcement learning on multi-turn tasks remains challenging due to sparse outcome rewards and difficult credit assignment across conversation turns. We present the first application of MT-GRPO…
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…
Reinforcement learning (RL) has emerged as a powerful tool for fine-tuning large language models (LLMs) to improve complex reasoning abilities. However, state-of-the-art policy optimization methods often suffer from high computational…
Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…
This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible…
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…
Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated…
Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal rewards, GRPO often stalls because rollouts within a group…
In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has been overlooked despite its potential to enhance online…
Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…
Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for summarisation learns a cross-input policy, which requires…
Reinforcement learning (RL) from unit-test feedback has become a standard post-training recipe for improving large language models (LLMs) on code generation. However, the pass-all-tests binary reward can be sparse, yielding no learning…
Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent faces a sequential decision-making…
Reinforcement learning (RL) post-training has become a trending paradigm for enhancing the capabilities of large language models (LLMs). Most existing RL systems for LLMs operate in a fully synchronous manner, where training must wait for…
We consider the problem of preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair instead of absolute…
Offline preference-based reinforcement learning (PbRL) provides an effective way to overcome the challenges of designing reward and the high costs of online interaction. However, since labeling preference needs real-time human feedback,…
Building a good predictive model requires an array of activities such as data imputation, feature transformations, estimator selection, hyper-parameter search and ensemble construction. Given the large, complex and heterogenous space of…
We propose a novel reinforcement learning (RL) design to optimize the charging strategy for autonomous mobile robots in large-scale block stacking warehouses. RL design involves a wide array of choices that can mostly only be evaluated…