Related papers: Meta Preference Learning for Fast User Adaptation …

Preference-based reinforcement learning (PbRL) has shown significant promise for personalization in human-robot interaction (HRI) by explicitly integrating human preferences into the robot learning process. However, existing practices often…

An important challenge in human-robot interaction (HRI) is enabling non-expert users to specify complex tasks for autonomous robots. Recently, active preference learning has been applied in HRI to interactively shape a robot's behavior. We…

Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods…

Human multi-robot system (MRS) collaboration is demonstrating potentials in wide application scenarios due to the integration of human cognitive skills and a robot team's powerful capability introduced by its multi-member structure.…

In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot be utilized for the new tasks. In this paper, we propose…

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…

In multi-behavior recommendation scenarios, analyzing users' diverse behaviors, such as click, purchase, and rating, enables a more comprehensive understanding of their interests, facilitating personalized and accurate recommendations. A…

The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. However,…

Physically Assistive Robots (PARs) require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause severe physical and cognitive fatigue for…

Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands. Scripting policies from scratch is intractable due to the high-dimensional control space, and training policies…

Robot policies need to adapt to human preferences and/or new environments. Human experts may have the domain knowledge required to help robots achieve this adaptation. However, existing works often require costly offline re-training on…

Simultaneous Machine Translation (SiMT) generates translations while receiving streaming source inputs. This requires the SiMT model to learn a read/write policy, deciding when to translate and when to wait for more source input. Numerous…

Generative, explainable, and flexible recommender systems, derived using Large Language Models (LLM) are promising and poorly adapted to the cold-start user situation, where there is little to no history of interaction. The current…

Aligning language models with human preferences through reinforcement learning from human feedback is crucial for their safe and effective deployment. The human preference is typically represented through comparison where one response is…

Humanoid locomotion requires not only accurate command tracking for navigation but also compliant responses to external forces during human interaction. Despite significant progress, existing RL approaches mainly emphasize robustness,…

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample…

Most reinforcement learning (RL) approaches for the decision-making of autonomous driving consider safety as a reward instead of a cost, which makes it hard to balance the tradeoff between safety and other objectives. Human risk preference…

Meta Reinforcement Learning (Meta-RL) has seen substantial advancements recently. In particular, off-policy methods were developed to improve the data efficiency of Meta-RL techniques. \textit{Probabilistic embeddings for actor-critic RL}…

Multi-objective reinforcement learning (MORL) is a structured approach for optimizing tasks with multiple objectives. However, it often relies on pre-defined reward functions, which can be hard to design for balancing conflicting goals and…

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…