Related papers: What Matters to You? Towards Visual Representation…
A well-designed reward is critical for effective reinforcement learning-based policy improvement. In real-world robotics, obtaining such rewards typically requires either labor-intensive human labeling or brittle, handcrafted objectives.…
With the advent of AI technologies, humans and robots are increasingly teaming up to perform collaborative tasks. To enable smooth and effective collaboration, the topic of value alignment (operationalized herein as the degree of dynamic…
Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions…
Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen tasks, due to their reliance on behavior cloning exclusively…
Reinforcement Learning (RL) has emerged as a powerful tool for neural combinatorial optimization, enabling models to learn heuristics that solve complex problems without requiring expert knowledge. Despite significant progress, existing RL…
Today's robots are increasingly interacting with people and need to efficiently learn inexperienced user's preferences. A common framework is to iteratively query the user about which of two presented robot trajectories they prefer. While…
Building a robot that can understand and learn to interact by watching humans has inspired several vision problems. However, despite some successful results on static datasets, it remains unclear how current models can be used on a robot…
Preference-based reinforcement learning (PbRL) is emerging as a promising approach to teaching robots through human comparative feedback, sidestepping the need for complex reward engineering. However, the substantial volume of feedback…
Reinforcement learning (RL) has become a powerful tool for post-training visual generative models, with Group Relative Policy Optimization (GRPO) increasingly used to align generators with human preferences. However, existing GRPO pipelines…
This paper explores multiple optimization methods to improve the performance of rating-based reinforcement learning (RbRL). RbRL, a method based on the idea of human ratings, has been developed to infer reward functions in reward-free…
With the increasing presence of robots in our every-day environments, improving their social skills is of utmost importance. Nonetheless, social robotics still faces many challenges. One bottleneck is that robotic behaviors need to be often…
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…
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…
This paper investigates image inpainting with preference alignment. Instead of introducing a novel method, we go back to basics and revisit fundamental problems in achieving such alignment. We leverage the prominent direct preference…
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…
While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…
Offline reinforcement learning (RL) provides a powerful framework for training robotic agents using pre-collected, suboptimal datasets, eliminating the need for costly, time-consuming, and potentially hazardous online interactions. This is…
Reinforcement learning (RL) has shown to be a valuable tool in training neural networks for autonomous motion planning. The application of RL to a specific problem is dependent on a reward signal to quantify how good or bad a certain action…
Learning from human involvement aims to incorporate the human subject to monitor and correct agent behavior errors. Although most interactive imitation learning methods focus on correcting the agent's action at the current state, they do…
Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…