相关论文: Reward Shaping to Mitigate Reward Hacking in RLHF

Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF) are pivotal methodologies in reward learning, which involve inferring and shaping the underlying reward function of sequential decision-making…

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RL from AI Feedback (RLAIF), introduced in…

A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models are susceptible to spurious features that are not causally…

Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…

Visuomotor robot policies, increasingly pre-trained on large-scale datasets, promise significant advancements across robotics domains. However, aligning these policies with end-user preferences remains a challenge, particularly when the…

Recent Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) increasingly use Reinforcement Learning (RL) for post-pretraining, such as RL with Verifiable Rewards (RLVR) for objective tasks and RL from Human Feedback (RLHF)…

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…

Reinforcement learning from human feedback (RLHF) offers a promising approach to aligning large language models (LLMs) with human preferences. Typically, a reward model is trained or supplied to act as a proxy for humans in evaluating…

Reinforcement learning from human feedback (RLHF) is a widely used method for aligning large language models with human preferences. However, RLHF often suffers from reward model overoptimisation, in which models overfit to the reward…

Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behaviour with human preferences. The traditional way to collect data in RLHF is via pairwise comparisons: human raters are asked to…

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

The main challenge in developing effective reinforcement learning (RL) pipelines is often the design and tuning the reward functions. Well-designed shaping reward can lead to significantly faster learning. Naively formulated rewards,…

Reinforcement Learning from Human Feedback (RLHF) is a widely used approach to align large-scale AI systems with human values. However, RLHF typically assumes a single, universal reward, which overlooks diverse preferences and limits…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic…

The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF can be resource-intensive and lead to scalability issues…

Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences…

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based…

Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering RLHF and advanced decoding strategies. While most prior work focuses on single-step generation, real-world applications increasingly…