相关论文: Hista and Numca: Estimate State Value Effectively …

The application of large language models to provide relevance assessments presents exciting opportunities to advance information retrieval, natural language processing, and beyond, but to date many unknowns remain. This paper reports on the…

Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize reasoning capacity beyond the base model. This raises a key…

Signal Temporal Logic (STL) is a powerful formal language for specifying real-time specifications of Cyber-Physical Systems (CPS). Transforming specifications written in natural language into STL formulas automatically has attracted…

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability…

Deep model-based Reinforcement Learning (RL) has the potential to substantially improve the sample-efficiency of deep RL. While various challenges have long held it back, a number of papers have recently come out reporting success with deep…

Reinforcement Learning (RL) is a powerful framework to address the discrepancy between loss functions used during training and the final evaluation metrics to be used at test time. When applied to neural Machine Translation (MT), it…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Reinforcement learning (RL) is a promising approach for optimizing HVAC control. RL offers a framework for improving system performance, reducing energy consumption, and enhancing cost efficiency. We benchmark two popular classical and deep…

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly…

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

This study investigates the effectiveness of reinforcement learning (RL) fine-tuning techniques on a compact language model (Qwen2.5-0.5B Base) for two challenging tasks: instruction following and mathematical reasoning. We compare…

Reinforcement learning from verifiable rewards (RLVR) stimulates the thinking processes of large language models (LLMs), substantially enhancing their reasoning abilities on verifiable tasks. It is often assumed that similar gains should…

Modern language models are evaluated on large benchmarks, which are difficult to make sense of, especially for model selection. Looking at the raw evaluation numbers themselves using a model-centric lens, we propose SimBA, a three phase…

We present an asymptotic analysis of Viterbi Training (VT) and contrast it with a more conventional Maximum Likelihood (ML) approach to parameter estimation in Hidden Markov Models. While ML estimator works by (locally) maximizing the…

Reinforcement learning (RL) involves performing exploratory actions in an unknown system. This can place a learning agent in dangerous and potentially catastrophic system states. Current approaches for tackling safe learning in RL…

Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves…

Collecting ground-truth rewards or human demonstrations for multi-step reasoning tasks is often prohibitively expensive, particularly in interactive domains such as web tasks. We introduce Self-Taught Lookahead (STL), a reward-free…

Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…

Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like…