Related papers: Representation Alignment from Human Feedback for C…
Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…
Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…
Generalist robot policies are trained on demonstrations collected across a wide variety of robots, scenes, and viewpoints. Yet it remains unclear how to best organize and scale such heterogeneous data so that it genuinely improves…
Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge…
Imitation learning for acquiring generalizable policies often requires a large volume of demonstration data, making the process significantly costly. One promising strategy to address this challenge is to leverage the cognitive and…
In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of…
Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…
In contextual linear bandits, the reward function is assumed to be a linear combination of an unknown reward vector and a given embedding of context-arm pairs. In practice, the embedding is often learned at the same time as the reward…
Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous…
Discovering effective reward functions remains a fundamental challenge in motor control of high-dimensional musculoskeletal systems. While humans can describe movement goals explicitly such as "walking forward with an upright posture," the…
Mirror neurons are a class of neurons that activate both when an individual observes an action and when they perform the same action. This mechanism reveals a fundamental interplay between action understanding and embodied execution,…
Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user. However, even for a single task, LfD may require numerous demonstrations. For versatile agents that must learn many tasks…
Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…
Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…
In human-in-the-loop reinforcement learning or environments where calculating a reward is expensive, the costly rewards can make learning efficiency challenging to achieve. The cost of obtaining feedback from humans or calculating expensive…
Human decision making can be challenging to predict because decisions are affected by a number of complex factors. Adding to this complexity, decision-making processes can differ considerably between individuals, and methods aimed at…
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…
Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which…
Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…
Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions…