相关论文: Learning Correlated Reward Models: Statistical Bar…

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

There is an extensive literature in social choice theory studying the consequences of weakening the assumptions of Arrow's Impossibility Theorem. Much of this literature suggests that there is no escape from Arrow-style impossibility…

Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely…

We present Preference Flow Matching (PFM), a new framework for preference-based reinforcement learning (PbRL) that streamlines the integration of preferences into an arbitrary class of pre-trained models. Existing PbRL methods require…

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…

Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefined reward functions. However, current PbRL methods face a critical challenge in effectively…

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Spurious correlations in a reward model's training data can prevent Reinforcement Learning from Human Feedback (RLHF) from identifying the desired goal and induce unwanted behaviors. This paper shows that offline RLHF is susceptible to…

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

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 shortcoming of batch reinforcement learning is its requirement for rewards in data, thus not applicable to tasks without reward functions. Existing settings for lack of reward, such as behavioral cloning, rely on optimal demonstrations…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Well-calibrated probabilistic regression models are a crucial learning component in robotics applications as datasets grow rapidly and tasks become more complex. Unfortunately, classical regression models are usually either probabilistic…

Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a…

Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}. While traditional methods rely on offline preference…

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a…

Reinforcement Learning from Human Feedback (RLHF) has played a crucial role in the success of large models such as ChatGPT. RLHF is a reinforcement learning framework which combines human feedback to improve learning effectiveness and…

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and…

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By…

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher…