相关论文: STRAPPER: Preference-based Reinforcement Learning …

We introduce Large Language Model-Assisted Preference Prediction (LAPP), a novel framework for robot learning that enables efficient, customizable, and expressive behavior acquisition with minimum human effort. Unlike prior approaches that…

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…

Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…

Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Specifying rewards for reinforcement learned (RL) agents is challenging. Preference-based RL (PbRL) mitigates these challenges by inferring a reward from feedback over sets of trajectories. However, the effectiveness of PbRL is limited by…

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…

In-context reinforcement learning (ICRL) leverages the in-context learning capabilities of transformer models (TMs) to efficiently generalize to unseen sequential decision-making tasks without parameter updates. However, existing ICRL…

Reinforcement Learning (RL) heavily relies on the careful design of the reward function. However, accurately assigning rewards to each state-action pair in Long-Term Reinforcement Learning (LTRL) tasks remains a significant challenge. As a…

Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…

Consistency regularization-based methods are prevalent in semi-supervised learning (SSL) algorithms due to their exceptional performance. However, they mainly depend on domain-specific data augmentations, which are not usable in domains…

Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for…

Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularized IRL applies strongly convex regularizers to the learner's…

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Offline reinforcement learning has become one of the most practical RL settings. However, most existing works on offline RL focus on the standard setting with scalar reward feedback. It remains unknown how to universally transfer the…

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…