相关论文: PEARL: PrEference Appraisal Reinforcement Learning…

This work introduces a preference learning method that ensures adherence to given specifications, with an application to autonomous vehicles. Our approach incorporates the priority ordering of Signal Temporal Logic (STL) formulas describing…

We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…

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…

Safe reinforcement learning (RL) is a standard paradigm for safety-critical decision making. However, real-world safety constraints can be complex, subjective, and even hard to explicitly specify. Existing works on constraint inference rely…

We present a novel unified bilevel optimization-based framework, \textsf{PARL}, formulated to address the recently highlighted critical issue of policy alignment in reinforcement learning using utility or preference-based feedback. We…

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…

Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces…

While reinforcement learning (RL) enables robots to acquire skills autonomously, its real-world deployment is severely limited by inefficient and unsafe exploration. Human-in-the-loop interventions offer a practical solution, yet existing…

Reinforcement Learning from Human Feedback (RLHF) has recently surged in popularity, particularly for aligning large language models and other AI systems with human intentions. At its core, RLHF can be viewed as a specialized instance of…

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on…

Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the sequence of actions does not require too much effort for…

In light of the significant progress made in the development and application of semantic segmentation tasks, there has been increasing attention towards improving the robustness of segmentation models against natural degradation factors…

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a…

Preference-based reinforcement learning (RL) provides a framework to train AI agents using human feedback through preferences over pairs of behaviors, enabling agents to learn desired behaviors when it is difficult to specify a numerical…

Multi-objective reinforcement learning (MORL) aims to find a set of high-performing and diverse policies that address trade-offs between multiple conflicting objectives. However, in practice, decision makers (DMs) often deploy only one or a…

Reinforcement Learning (RL)-based motion planning has recently shown the potential to outperform traditional approaches from autonomous navigation to robot manipulation. In this work, we focus on a motion planning task for an evasive target…

Preference-based reinforcement learning (PbRL) bypasses complex reward engineering by learning rewards directly from human preferences, enabling better alignment with human intentions. However, its effectiveness in multi-stage tasks, where…

As multi-robot systems (MRS) are widely used in various tasks such as natural disaster response and social security, people enthusiastically expect an MRS to be ubiquitous that a general user without heavy training can easily operate.…

Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algorithms and active querying techniques have been proposed as a…

We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting…