Yuchen Cui

Yuchen Cui, Siddharth Karamcheti, Raj Palleti et al. · stanford

Systems for language-guided human-robot interaction must satisfy two key desiderata for broad adoption: adaptivity and learning efficiency. Unfortunately, existing instruction-following agents cannot adapt, lacking the ability to incorporate online natural language supervision, and even if they could, require hundreds of demonstrations to learn even simple policies. In this work, we address these problems by presenting Language-Informed Latent Actions with Corrections (LILAC), a framework for incorporating and adapting to natural language corrections - "to the right," or "no, towards the book" - online, during execution. We explore rich manipulation domains within a shared autonomy paradigm. Instead of discrete turn-taking between a human and robot, LILAC splits agency between the human and robot: language is an input to a learned model that produces a meaningful, low-dimensional control space that the human can use to guide the robot. Each real-time correction refines the human's control space, enabling precise, extended behaviors - with the added benefit of requiring only a handful of demonstrations to learn. We evaluate our approach via a user study where users work with a Franka Emika Panda manipulator to complete complex manipulation tasks. Compared to existing learned baselines covering both open-loop instruction following and single-turn shared autonomy, we show that our corrections-aware approach obtains higher task completion rates, and is subjectively preferred by users because of its reliability, precision, and ease of use.

Suneel Belkhale, Yuchen Cui, Dorsa Sadigh

In supervised learning, the question of data quality and curation has been over-shadowed in recent years by increasingly more powerful and expressive models that can ingest internet-scale data. However, in offline learning for robotics, we simply lack internet scale data, and so high quality datasets are a necessity. This is especially true in imitation learning (IL), a sample efficient paradigm for robot learning using expert demonstrations. Policies learned through IL suffer from state distribution shift at test time due to compounding errors in action prediction, which leads to unseen states that the policy cannot recover from. Instead of designing new algorithms to address distribution shift, an alternative perspective is to develop new ways of assessing and curating datasets. There is growing evidence that the same IL algorithms can have substantially different performance across different datasets. This calls for a formalism for defining metrics of "data quality" that can further be leveraged for data curation. In this work, we take the first step toward formalizing data quality for imitation learning through the lens of distribution shift: a high quality dataset encourages the policy to stay in distribution at test time. We propose two fundamental properties that shape the quality of a dataset: i) action divergence: the mismatch between the expert and learned policy at certain states; and ii) transition diversity: the noise present in the system for a given state and action. We investigate the combined effect of these two key properties in imitation learning theoretically, and we empirically analyze models trained on a variety of different data sources. We show that state diversity is not always beneficial, and we demonstrate how action divergence and transition diversity interact in practice.

Lihan Zha, Yuchen Cui, Li-Heng Lin et al.

Today's robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedback that can be arbitrary corrections about high-level human preferences to low-level adjustments to skill parameters. In this work, we present Distillation and Retrieval of Online Corrections (DROC), a large language model (LLM)-based system that can respond to arbitrary forms of language feedback, distill generalizable knowledge from corrections, and retrieve relevant past experiences based on textual and visual similarity for improving performance in novel settings. DROC is able to respond to a sequence of online language corrections that address failures in both high-level task plans and low-level skill primitives. We demonstrate that DROC effectively distills the relevant information from the sequence of online corrections in a knowledge base and retrieves that knowledge in settings with new task or object instances. DROC outperforms other techniques that directly generate robot code via LLMs by using only half of the total number of corrections needed in the first round and requires little to no corrections after two iterations. We show further results, videos, prompts and code on https://sites.google.com/stanford.edu/droc .

Li-Heng Lin, Yuchen Cui, Amber Xie et al.

Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant past experiences to augment this target data when learning policies. However, existing data retrieval methods fall under two extremes: they either rely on the existence of exact behaviors with visually similar scenes in the prior data, which is impractical to assume; or they retrieve based on semantic similarity of high-level language descriptions of the task, which might not be that informative about the shared low-level behaviors or motions across tasks that is often a more important factor for retrieving relevant data for policy learning. In this work, we investigate how we can leverage motion similarity in the vast amount of cross-task data to improve few-shot imitation learning of the target task. Our key insight is that motion-similar data carries rich information about the effects of actions and object interactions that can be leveraged during few-shot adaptation. We propose FlowRetrieval, an approach that leverages optical flow representations for both extracting similar motions to target tasks from prior data, and for guiding learning of a policy that can maximally benefit from such data. Our results show FlowRetrieval significantly outperforms prior methods across simulated and real-world domains, achieving on average 27% higher success rate than the best retrieval-based prior method. In the Pen-in-Cup task with a real Franka Emika robot, FlowRetrieval achieves 3.7x the performance of the baseline imitation learning technique that learns from all prior and target data. Website: https://flow-retrieval.github.io

Yuchen Cui, Scott Niekum, Abhinav Gupta et al.

Task specification is at the core of programming autonomous robots. A low-effort modality for task specification is critical for engagement of non-expert end-users and ultimate adoption of personalized robot agents. A widely studied approach to task specification is through goals, using either compact state vectors or goal images from the same robot scene. The former is hard to interpret for non-experts and necessitates detailed state estimation and scene understanding. The latter requires the generation of desired goal image, which often requires a human to complete the task, defeating the purpose of having autonomous robots. In this work, we explore alternate and more general forms of goal specification that are expected to be easier for humans to specify and use such as images obtained from the internet, hand sketches that provide a visual description of the desired task, or simple language descriptions. As a preliminary step towards this, we investigate the capabilities of large scale pre-trained models (foundation models) for zero-shot goal specification, and find promising results in a collection of simulated robot manipulation tasks and real-world datasets.

Yilun Hao, Ruinan Wang, Zhangjie Cao et al.

Multimodal demonstrations provide robots with an abundance of information to make sense of the world. However, such abundance may not always lead to good performance when it comes to learning sensorimotor control policies from human demonstrations. Extraneous data modalities can lead to state over-specification, where the state contains modalities that are not only useless for decision-making but also can change data distribution across environments. State over-specification leads to issues such as the learned policy not generalizing outside of the training data distribution. In this work, we propose Masked Imitation Learning (MIL) to address state over-specification by selectively using informative modalities. Specifically, we design a masked policy network with a binary mask to block certain modalities. We develop a bi-level optimization algorithm that learns this mask to accurately filter over-specified modalities. We demonstrate empirically that MIL outperforms baseline algorithms in simulated domains including MuJoCo and a robot arm environment using the Robomimic dataset, and effectively recovers the environment-invariant modalities on a multimodal dataset collected on a real robot. Our project website presents supplemental details and videos of our results at: https://tinyurl.com/masked-il

Omar Rayyan, Maximilian Gillesm, Yuchen Cui

Despite increasing dataset scale and model capacity, robot manipulation policies still struggle to generalize beyond their training distributions. As a result, deploying state-of-the-art policies in new environments, tasks, or robot embodiments often requires collecting additional demonstrations. Enabling this in real-world deployment settings requires tools that allow users to collect demonstrations quickly, affordably, and with minimal setup. We present TeleDex, an open-source system for intuitive teleoperation of dexterous hands and robotic manipulators using any readily available phone. The system streams low-latency 6-DoF wrist poses and articulated 21-DoF hand state estimates from the phone, which are retargeted to robot arms and multi-fingered hands without requiring external tracking infrastructure. TeleDex supports both a handheld phone-only mode and an optional 3D-printable hand-mounted interface for finger-level teleoperation. By lowering the hardware and setup barriers to dexterous teleoperation, TeleDex enables users to quickly collect demonstrations during deployment to support policy fine-tuning. We evaluate the system across simulation and real-world manipulation tasks, demonstrating its effectiveness as a unified scalable interface for robot teleoperation. All software and hardware designs, along with demonstration videos, are open-source and available at orayyan.com/teledex.

Megha Srivastava, Jonathan Ouyang, Eric Zhou et al.

Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections. We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states estimated to be most learnable. We first show that PSN outperforms existing shared autonomy baselines in balancing student improvement in unassisted reward with overall shared performance, using simulated students in the classic LunarLander environment. We then present, to the best of our knowledge, the first human subject studies of a planner incorporating learning-compatible shared autonomy: across two driving tasks in the CARLA simulator (High Performance Racing and Parallel Parking, n = 60), PSN produces up to 7x larger gains in unassisted skill than standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice.

Sangyun Park, Jin Kim, Yuchen Cui et al.

Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive. In this work, we introduce TRACE (Textual Reasoning for Affordance Coordinate Extraction), a novel methodology that integrates a textual Chain of Reasoning (CoR) into the affordance prediction process. We use this methodology to create the TRACE dataset, a large-scale collection created via an autonomous pipeline that pairs instructions with explicit textual rationales. By fine-tuning a VLM on this data, our model learns to externalize its spatial reasoning before acting. Our experiments show that our TRACE-tuned model achieves state-of-the-art performance, reaching 48.1% accuracy on the primary Where2Place (W2P) benchmark (a 9.6% relative improvement) and 55.0% on the more challenging W2P(h) subset. Crucially, an ablation study demonstrates that performance scales directly with the amount of reasoning data used, confirming the CoR's effectiveness. Furthermore, analysis of the model's attention maps reveals an interpretable reasoning process where focus shifts dynamically across reasoning steps. This work shows that training VLMs to generate a textual CoR is an effective and robust strategy for enhancing the precision, reliability, and interpretability of VLM-based robot control. Our dataset and code are available at https://github.com/jink-ucla/TRACE

Andy Wang, Xu Yan, Brandon McMahan et al.

Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is subject to corruption, shared autonomy can significantly increase task performance by using a trained copilot to effectively correct user actions in a manner consistent with the user's goals. To significantly improve the performance of shared autonomy, we introduce Diffusion Sequence Copilots (DiSCo): a method of shared autonomy with diffusion policy that plans action sequences consistent with past user actions. DiSCo seeds and inpaints the diffusion process with user-provided actions with hyperparameters to balance conformity to expert actions, alignment with user intent, and perceived responsiveness. We demonstrate that DiSCo substantially improves task performance in simulated driving and robotic arm tasks. Project website: https://sites.google.com/view/disco-shared-autonomy/

Yejin Kim, Wilbert Pumacay, Omar Rayyan et al.

Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k diverse indoor environments, ranging from handcrafted household scenes to procedurally generated multiroom houses, populated with 130k richly annotated object assets, including 48k manipulable objects with 42M stable grasps. Crucially, these environments are simulator-agnostic, supporting popular options such as MuJoCo, Isaac, and ManiSkill. The ecosystem supports the full spectrum of embodied tasks: static and mobile manipulation, navigation, and multiroom long-horizon tasks requiring coordinated perception, planning, and interaction across entire indoor environments. We also design MolmoSpaces-Bench, a benchmark suite of 8 tasks in which robots interact with our diverse scenes and richly annotated objects. Our experiments show MolmoSpaces-Bench exhibits strong sim-to-real correlation (R = 0.96, \r{ho} = 0.98), confirm newer and stronger zero-shot policies outperform earlier versions in our benchmarks, and identify key sensitivities to prompt phrasing, initial joint positions, and camera occlusion. Through MolmoSpaces and its open-source assets and tooling, we provide a foundation for scalable data generation, policy training, and benchmark creation for robot learning research.

Alvin Zhu, Mingzhang Zhu, Beom Jun Kim et al.

Scaling dexterous robot learning is constrained by the difficulty of collecting high-quality demonstrations across diverse operators. Existing wearable interfaces often trade comfort and cross-user adaptability for kinematic fidelity, while embodiment mismatch between demonstration and deployment requires visual post-processing before policy training. We present DexEXO, a wearability-first hand exoskeleton that aligns visual appearance, contact geometry, and kinematics at the hardware level. DexEXO features a pose-tolerant thumb mechanism and a slider-based finger interface analytically modeled to support hand lengths from 140~mm to 217~mm, reducing operator-specific fitting and enabling scalable cross-operator data collection. A passive hand visually matches the deployed robot, allowing direct policy training from raw wrist-mounted RGB observations. User studies demonstrate improved comfort and usability compared to prior wearable systems. Using visually aligned observations alone, we train diffusion policies that achieve competitive performance while substantially simplifying the end-to-end pipeline. These results show that prioritizing wearability and hardware-level embodiment alignment reduces both human and algorithmic bottlenecks without sacrificing task performance. Project Page: https://dexexo-research.github.io/

Haozhuo Li, Yuchen Cui, Dorsa Sadigh

Imitation learning is a promising approach for learning robot policies with user-provided data. The way demonstrations are provided, i.e., demonstration modality, influences the quality of the data. While existing research shows that kinesthetic teaching (physically guiding the robot) is preferred by users for the intuitiveness and ease of use, the majority of existing manipulation datasets were collected through teleoperation via a VR controller or spacemouse. In this work, we investigate how different demonstration modalities impact downstream learning performance as well as user experience. Specifically, we compare low-cost demonstration modalities including kinesthetic teaching, teleoperation with a VR controller, and teleoperation with a spacemouse controller. We experiment with three table-top manipulation tasks with different motion constraints. We evaluate and compare imitation learning performance using data from different demonstration modalities, and collected subjective feedback on user experience. Our results show that kinesthetic teaching is rated the most intuitive for controlling the robot and provides cleanest data for best downstream learning performance. However, it is not preferred as the way for large-scale data collection due to the physical load. Based on such insight, we propose a simple data collection scheme that relies on a small number of kinesthetic demonstrations mixed with data collected through teleoperation to achieve the best overall learning performance while maintaining low data-collection effort.

Zhi Zhang, Chris Chow, Yasi Zhang et al.

Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from a task distribution. We propose EPIC (Empirical PAC-Bayes that Improves Continuously), a novel algorithm designed for lifelong RL using PAC-Bayes theory. EPIC learns a shared policy distribution, referred to as the world policy, which enables rapid adaptation to new tasks while retaining valuable knowledge from previous experiences. Our theoretical analysis establishes a relationship between the algorithm's generalization performance and the number of prior tasks preserved in memory. We also derive the sample complexity of EPIC in terms of RL regret. Extensive experiments on a variety of environments demonstrate that EPIC significantly outperforms existing methods in lifelong RL, offering both theoretical guarantees and practical efficacy through the use of the world policy.

Soham Kulkarni, Raayan Dhar, Yuchen Cui

In behavioral cloning (BC), policy performance is fundamentally limited by demonstration data quality. Real-world datasets contain trajectories of varying quality due to operator skill differences, teleoperation artifacts, and procedural inconsistencies, yet standard BC treats all demonstrations equally. Existing curation methods require costly policy training in the loop or manual annotation, limiting scalability. We propose RINSE (Ranking and INdexing Smooth Examples), a lightweight framework for scoring demonstrations based on trajectory smoothness that is policy-architecture-agnostic and operates on trajectory data alone, with TED additionally using a phase-boundary/contact signal. Grounded in motor control theory, which establishes smoothness as a hallmark of skilled movement, RINSE uses two complementary metrics: Spectral Arc Length (SAL), a spectral measure of frequency-domain regularity, and Trajectory-Envelope Distance (TED), a spatial measure of contact-aware geometric deviation. We show that smoothness filtering can reduce the conditional action variance of the retained data distribution, with downstream effects that can be amplified by action chunking and compounding error. On RoboMimic benchmarks, SAL filtering achieves 16% higher success using one-sixth of the data. On real-world manipulation, TED filtering achieves 20% improvement with half the data. As a retrieval-stage filter within STRAP on LIBERO-10, RINSE re-ranking improves mean success by 5.6%. As soft weights in Re-Mix domain reweighting, RINSE scores produce domain allocations highly correlated with the learned Re-Mix allocations (Spearman $ρ\geq 0.89$). These results support smoothness as a useful quality signal across filtering, retrieval, and reweighting settings, especially in noisy or heterogeneous data regimes.

Megha Srivastava, Reihaneh Iranmanesh, Yuchen Cui et al.

Motor skill learning often requires experienced professionals who can provide personalized instruction. Unfortunately, the availability of high-quality training can be limited for specialized tasks, such as high performance racing. Several recent works have leveraged AI-assistance to improve instruction of tasks ranging from rehabilitation to surgical robot tele-operation. However, these works often make simplifying assumptions on the student learning process, and fail to model how a teacher's assistance interacts with different individuals' abilities when determining optimal teaching strategies. Inspired by the idea of scaffolding from educational psychology, we leverage shared autonomy, a framework for combining user inputs with robot autonomy, to aid with curriculum design. Our key insight is that the way a student's behavior improves in the presence of assistance from an autonomous agent can highlight which sub-skills might be most ``learnable'' for the student, or within their Zone of Proximal Development. We use this to design Z-COACH, a method for using shared autonomy to provide personalized instruction targeting interpretable task sub-skills. In a user study (n=50), where we teach high performance racing in a simulated environment of the Thunderhill Raceway Park with the CARLA Autonomous Driving simulator, we show that Z-COACH helps identify which skills each student should first practice, leading to an overall improvement in driving time, behavior, and smoothness. Our work shows that increasingly available semi-autonomous capabilities (e.g. in vehicles, robots) can not only assist human users, but also help *teach* them.

Joshua Li, Fernando Jose Pena Cantu, Emily Yu et al.

Video Scene Graph Generation (VidSGG) is an important topic in understanding dynamic kitchen environments. Current models for VidSGG require extensive training to produce scene graphs. Recently, Vision Language Models (VLM) and Vision Foundation Models (VFM) have demonstrated impressive zero-shot capabilities in a variety of tasks. However, VLMs like Gemini struggle with the dynamics for VidSGG, failing to maintain stable object identities across frames. To overcome this limitation, we propose SAMJAM, a zero-shot pipeline that combines SAM2's temporal tracking with Gemini's semantic understanding. SAM2 also improves upon Gemini's object grounding by producing more accurate bounding boxes. In our method, we first prompt Gemini to generate a frame-level scene graph. Then, we employ a matching algorithm to map each object in the scene graph with a SAM2-generated or SAM2-propagated mask, producing a temporally-consistent scene graph in dynamic environments. Finally, we repeat this process again in each of the following frames. We empirically demonstrate that SAMJAM outperforms Gemini by 8.33% in mean recall on the EPIC-KITCHENS and EPIC-KITCHENS-100 datasets.

Mingzhang Zhu, Alvin Zhu, Jose Victor S. H. Ramos et al.

Scalable learning of dexterous manipulation remains bottlenecked by the difficulty of collecting natural, high-fidelity human demonstrations of multi-finger hands due to occlusion, complex hand kinematics, and contact-rich interactions. We present WHED, a wearable hand-exoskeleton system designed for in-the-wild demonstration capture, guided by two principles: wearability-first operation for extended use and a pose-tolerant, free-to-move thumb coupling that preserves natural thumb behaviors while maintaining a consistent mapping to the target robot thumb degrees of freedom. WHED integrates a linkage-driven finger interface with passive fit accommodation, a modified passive hand with robust proprioceptive sensing, and an onboard sensing/power module. We also provide an end-to-end data pipeline that synchronizes joint encoders, AR-based end-effector pose, and wrist-mounted visual observations, and supports post-processing for time alignment and replay. We demonstrate feasibility on representative grasping and manipulation sequences spanning precision pinch and full-hand enclosure grasps, and show qualitative consistency between collected demonstrations and replayed executions.

Huihan Liu, Rutav Shah, Shuijing Liu et al. · cmu

Assistive teleoperation, where control is shared between a human and a robot, enables efficient and intuitive human-robot collaboration in diverse and unstructured environments. A central challenge in real-world assistive teleoperation is for the robot to infer a wide range of human intentions from user control inputs and to assist users with correct actions. Existing methods are either confined to simple, predefined scenarios or restricted to task-specific data distributions at training, limiting their support for real-world assistance. We introduce Casper, an assistive teleoperation system that leverages commonsense knowledge embedded in pre-trained visual language models (VLMs) for real-time intent inference and flexible skill execution. Casper incorporates an open-world perception module for a generalized understanding of novel objects and scenes, a VLM-powered intent inference mechanism that leverages commonsense reasoning to interpret snippets of teleoperated user input, and a skill library that expands the scope of prior assistive teleoperation systems to support diverse, long-horizon mobile manipulation tasks. Extensive empirical evaluation, including human studies and system ablations, demonstrates that Casper improves task performance, reduces human cognitive load, and achieves higher user satisfaction than direct teleoperation and assistive teleoperation baselines. More information is available at https://ut-austin-rpl.github.io/casper/

Muhammad Qasim Ali, Saeejith Nair, Alexander Wong et al.

Structured scene representations are a core component of embodied agents, helping to consolidate raw sensory streams into readable, modular, and searchable formats. Due to their high computational overhead, many approaches build such representations in advance of the task. However, when the task specifications change, such static approaches become inadequate as they may miss key objects, spatial relations, and details. We introduce GraphPad, a modifiable structured memory that an agent can tailor to the needs of the task through API calls. It comprises a mutable scene graph representing the environment, a navigation log indexing frame-by-frame content, and a scratchpad for task-specific notes. Together, GraphPad serves as a dynamic workspace that remains complete, current, and aligned with the agent's immediate understanding of the scene and its task. On the OpenEQA benchmark, GraphPad attains 55.3%, a +3.0% increase over an image-only baseline using the same vision-language model, while operating with five times fewer input frames. These results show that allowing online, language-driven refinement of 3-D memory yields more informative representations without extra training or data collection.

Yuchen Cui, Qiping Zhang, Alessandro Allievi et al.

Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. A robot or other agent could leverage an understanding of such implicit human feedback to improve its task performance at no cost to the human. This approach contrasts with common agent teaching methods based on demonstrations, critiques, or other guidance that need to be attentively and intentionally provided. In this paper, we first define the general problem of learning from implicit human feedback and then propose to address this problem through a novel data-driven framework, EMPATHIC. This two-stage method consists of (1) mapping implicit human feedback to relevant task statistics such as reward, optimality, and advantage; and (2) using such a mapping to learn a task. We instantiate the first stage and three second-stage evaluations of the learned mapping. To do so, we collect a dataset of human facial reactions while participants observe an agent execute a sub-optimal policy for a prescribed training task. We train a deep neural network on this data and demonstrate its ability to (1) infer relative reward ranking of events in the training task from prerecorded human facial reactions; (2) improve the policy of an agent in the training task using live human facial reactions; and (3) transfer to a novel domain in which it evaluates robot manipulation trajectories.

Yuchen Cui, David Isele, Scott Niekum et al.

Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.

Daniel S. Brown, Yuchen Cui, Scott Niekum

Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. Utilizing recent advances in performance bounds for inverse reinforcement learning, we propose a risk-aware active inverse reinforcement learning algorithm that focuses active queries on areas of the state space with the potential for large generalization error. We show that risk-aware active learning outperforms standard active IRL approaches on gridworld, simulated driving, and table setting tasks, while also providing a performance-based stopping criterion that allows a robot to know when it has received enough demonstrations to safely perform a task.