Robot learning from humans has been proposed and researched for several decades as a means to enable robots to learn new skills or adapt existing ones to new situations. Recent advances in AI, including learning approaches like reinforcement learning and architectures like transformers and foundation models, combined with access to massive datasets, have created attractive opportunities to apply those data-hungry techniques to this problem. We argue that the focus on massive amounts of pre-collected data, and the resulting learning paradigm, where humans demonstrate and robots learn in isolation, is overshadowing a specialized area of work we term Human-Interactive Robot Learning (HIRL). This paradigm, wherein robots and humans interact during the learning process , is at the intersection of multiple fields (AI, robotics, human–computer interaction, design and others) and holds unique promise. Using HIRL, robots can achieve greater sample efficiency (as humans can provide task knowledge through interaction), align with human preferences (as humans can guide the robot behavior toward their expectations), and explore more meaningfully and safely (as humans can utilize domain knowledge to guide learning and prevent catastrophic failures). This can result in robotic systems that can more quickly and easily adapt to new tasks in human environments. The objective of this article is to provide a broad and consistent overview of HIRL research and to guide researchers toward understanding the scope of HIRL, and current open or underexplored challenges related to four themes—namely, human, robot learning, interaction, and broader context. The article includes concrete use cases to illustrate the interaction between these challenges and inspire further research according to broad recommendations and a call for action for the growing HIRL community.

Millions of people cannot eat independently due to a disability, and caregiver-assisted meals can make them feel self-conscious, pressured, or burdensome. Robot-assisted feeding promises to empower people with motor impairments to feed themselves. However, current research typically examines specific robotic system subcomponents and evaluates them in controlled lab settings. This leaves a gap in developing and evaluating an end-to-end system that can feed entire meals in out-of-lab settings. We present one such system, which we developed collaboratively with two community researchers (CRs) with motor-impairments. The key challenge of developing a robot feeding system for out-of-lab use is the varied off-nominal scenarios that inevitably arise. Our key insight is that users can overcome many off-nominals, provided customizability and control over the system. Our system improves upon the state-of-the-art with: (1) a user interface that provides substantial user customizability and control, (2) a bite selection implementation that incorporates users-in-the-loop to generalize across food items, and (3) portable hardware that facilitates system use in diverse environments without inhibiting user mobility. We conduct two studies to evaluate the system. In Study 1, five users with motor impairments and one CR use the system to feed themselves meals of their choice in a cafeteria, office, or conference room. In Study 2, one CR uses the system in his home for five days, feeding himself 10 meals across diverse contexts. We present 3 key lesson learned: (1) spatial contexts are numerous, customizability lets users adapt to them; (2) off-nominals will arise, variable autonomy lets users overcome them; and (3) assistive robots' benefits depend on context. We provide video footage and code on our website.

Robots can incorporate data from human teachers when learning new tasks. However, this data can often be noisy, which can cause robots to learn slowly or not at all. One method for learning from human teachers is Human-in-the-loop Reinforcement Learning (HRL), which can combine information from both an environmental reward and external feedback from human teachers. However, many HRL methods assume near-perfect information from teachers or must know the skill level of each teacher before starting the learning process. Our algorithm, Classification for Learning Erroneous Assessments using Rewards (CLEAR), is a feedback filter for Reinforcement Learning (RL) algorithms, enabling learning agents to learn from imperfect teachers without prior modeling. CLEAR is able to determine whether human feedback is correct based on observations of the RL learning curve. Our results suggest that CLEAR improves the quality of human feedback - from 57.5% to 65% correct in a human study - and performs more reliably than baselines by matching or outperforming RL without human teachers in all tested cases.

With robots poised to enter our daily environments, we conjecture that they will not only need to work for people, but also learn from them. An active area of investigation in the robotics, machine learning, and human-robot interaction communities is the design of teachable robotic agents that can learn interactively from human input. To refer to these research efforts, we use the umbrella term Human-Interactive Robot Learning (HIRL). While algorithmic solutions for robots learning from people have been investigated in a variety of ways, HIRL, as a fairly new research area, is still lacking: 1) a formal set of definitions to classify related but distinct research problems or solutions, 2) benchmark tasks, interactions, and metrics to evaluate the performance of HIRL algorithms and interactions, and 3) clear long-term research challenges to be addressed by different communities. The main goal of this workshop will be to consolidate relevant recent work falling under the HIRL umbrella into a coherent set of long, medium, and short-term research problems, and identify the most pressing future research goals in this area. As HIRL is a developing research area, this workshop is an opportunity to break the existing boundaries between relevant research communities by developing and sharing a diverse set of benchmark tasks and metrics for HIRL, inspired by other fields including neuroscience, biology, and ethics research.

Policy Shaping is a Human-in-the-loop Reinforcement Learning (HRL) algorithm. We extend this work to continuous states with our algorithm, Deep Policy Shaping (DPS). DPS uses a feedback neural network that learns the optimality of actions from noisy feedback combined with an RL algorithm. In simulation, we find that DPS outperforms or matches baselines averaged over multiple hyperparameter settings and varying feedback correctness.

Interactive Reinforcement Learning (RL) enables agents to learn from two sources: rewards taken from observations of the environment, and feedback or advice from a secondary critic source, such as human teachers or sensor feedback. The addition of information from a critic during the learning process allows the agents to learn more quickly than non-interactive RL. There are many methods that allow policy feedback or advice to be combined with RL. However, critics can often give imperfect information. In this work, we introduce a framework for characterizing Interactive RL methods with imperfect teachers and propose an algorithm, Revision Estimation from Partially Incorrect Resources (REPaIR), which can estimate corrections to imperfect feedback over time. We run experiments both in simulations and demonstrate performance on a physical robot, and find that when baseline algorithms do not have prior information on the exact quality of a feedback source, using REPaIR matches or improves the expected performance of these algorithms.

For robots to be perceived as full-fledged team members, they must display intelligent behavior along multiple dimensions. One challenge is that even when the robot and human are on the same team, the interaction may not feel like teamwork to the human. We present a novel algorithm, Teammate Algorithm for Shared Cooperation (TASC). TASC is motivated by the concept of shared cooperative activity (SCA) for human-human teamwork, developed in prior work by Bratman. We focus on enabling the robot to prioritize certain SCA facets in its action selection depending on the task. We evaluated TASC in three experiments using different tasks with human users on Amazon Mechanical Turk. Our results show that TASC enabled participants to predict the robot's goal earlier by one robot move and with greater confidence. The robot also helped reduce participants' energy usage in a simulated block-moving task. Altogether, these results show that considering the SCA facets in the robot's action selection improves teamwork.

Robots deployed for long periods of time need to be able to explore and learn from their environment. One approach to this problem has been reinforcement learning (RL), in which robots receive rewards from the environment that allow them to choose optimal actions. To speed learning when human supervision is available, interactive reinforcement learning solicits feedback from a human teacher. However, this approach typically assumes that learning takes place under continuous supervision, which is unlikely to hold in long-term scenarios. We propose an extension to a method of interactive reinforcement learning, policy shaping, that takes into account human attention. Our approach enables better performance while unattended by favoring information-gathering actions when attended and actions that have received positive feedback when unattended. We test our approach in both simulation and on a robot, finding that our method learns faster than policy shaping and performs more safely than policy shaping while no one is paying attention to the robot.

In exploring representative databases, a primary issue has been finding accurate models of user preferences. Given this, our work generalizes the method of regret minimization as proposed by Nanongkai et al. to include nonlinear utility functions. Regret minimization is an approach for selecting k representative points from a database such that every user's ideal point in the entire database is similar to one of the k points. This approach combines benefits of the methods top- k and skyline; it controls the size of the output but does not require knowledge of users' preferences. Prior work with k -regret queries assumes users' preferences to be modeled by linear utility functions. In this paper, we derive upper and lower bounds for nonlinear utility functions, as these functions can better fit occurrences such as diminishing marginal returns, propensity for risk, and substitutability of preferences. To model these phenomena, we analyze a broad subset of convex, concave, and constant elasticity of substitution functions. We also run simulations on real and synthetic data to prove the efficacy of our bounds in practice.