AIConfPaper
← Search

Andrey Kolobov

22 accepted papers

2026

Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning

Patrick Yin, Tyler Westenbroek, Zhengyu Zhang, Ignacio Dagnino, Eeshani Shilamkar, Numfor Mbiziwo-Tiapo +5
ICLR 2026poster

Reinforcement learning in GPU-enabled physics simulation has been the driving force behind many of the breakthroughs in sim-to-real robot learning. However, current approaches for data generation in simulation are unwieldy and task-specific, requiring extensive human effort to engineer training curr…

Cited by 0Source ↗Scholar ↗
2026

TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models

Hokyun Im, Euijin Jeong, Andrey Kolobov, Jianlong Fu, Youngwoon Lee
ICLR 2026poster

Vision-language-action models (VLAs) trained on large-scale robotic datasets have demonstrated strong performance on manipulation tasks, including bimanual tasks. However, because most public datasets focus on single-arm demonstrations, adapting VLAs for bimanual tasks typically requires substantial…

Cited by 0Source ↗Scholar ↗
2025

Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning

Patrick Yin, Tyler Westenbroek, Ching-An Cheng, Andrey Kolobov, Abhishek Gupta
ICLR 2025poster

Robot learning requires a considerable amount of high-quality data to realize the promise of generalization. However, large data sets are costly to collect in the real world. Physics simulators can cheaply generate vast data sets with broad coverage over states, actions, and environments. However, p…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

SITE: towards Spatial Intelligence Thorough Evaluation

Wenqi Wang, Reuben Tan, Pengyue Zhu, Jianwei Yang, Zhengyuan Yang, Lijuan Wang +3
ICCV 2025poster

Spatial intelligence (SI) represents a cognitive ability encompassing the visualization, manipulation, and reasoning about spatial relationships, underpinning disciplines from neuroscience to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

Ruijie Zheng, Yongyuan Liang, Shuaiyi Huang, Jianfeng Gao, Hal Daumé III, Andrey Kolobov +2
ICLR 2025poster

Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less effective in handling complex tasks, such as manipulation.…

Cited by 8Source ↗PDF ↗Scholar ↗
2024

PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control

Ruijie Zheng, Ching-An Cheng, Hal Daumé III, Furong Huang, Andrey Kolobov
ICML 2024oral

Temporal action abstractions, along with belief state representations, are a powerful knowledge sharing mechanism for sequential decision making. In this work, we propose a novel view that treats inducing temporal action abstractions as a sequence compression problem. To do so, we bring a subtle but…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2024

Watching the Air Rise: Learning-Based Single-Frame Schlieren Detection

Florian Achermann, Julian Andreas Haug, Tobias Zumsteg, Nicholas Lawrance, Jen Jen Chung, Andrey Kolobov +1
ICRA 2024poster

Detecting air flows caused by phenomena such as heat convection is valuable in multiple scenarios, including leak identification and locating thermal updrafts for extending UAV flight duration. Unfortunately, the heat signature of these flows is often too subtle to be seen by a thermal camera. While…

Cited by 0Source ↗Scholar ↗
2023

Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control

Vivek Myers, Andre Wang He, Kuan Fang, Homer Rich Walke, Philippe Hansen-Estruch, Ching-An Cheng +4
CoRL 2023poster

Our goal is for robots to follow natural language instructions like ``put the towel next to the microwave.'' But getting large amounts of labeled data, i.e. data that contains demonstrations of tasks labeled with the language instruction, is prohibitive. In contrast, obtaining policies that respond…

Cited by 32Source ↗Scholar ↗
2023

PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining

Garrett Thomas, Ching-An Cheng, Ricky Loynd, Felipe Vieira Frujeri, Vibhav Vineet, Mihai Jalobeanu +1
CoRL 2023poster

A rich representation is key to general robotic manipulation, but existing approaches to representation learning require large amounts of multimodal demonstrations. In this work we propose PLEX, a transformer-based architecture that learns from a small amount of task-agnostic visuomotor trajectories…

Cited by 12Source ↗Scholar ↗
2023

Survival Instinct in Offline Reinforcement Learning

Anqi Li, Dipendra Misra, Andrey Kolobov, Ching-An Cheng
NeurIPS 2023spotlight

We present a novel observation about the behavior of offline reinforcement learning (RL) algorithms: on many benchmark datasets, offline RL can produce well-performing and safe policies even when trained with "wrong" reward labels, such as those that are zero everywhere or are negatives of the true…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2022

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

Bogdan Mazoure, Ahmed M Ahmed, R Devon Hjelm, Andrey Kolobov, Patrick MacAlpine
ICLR 2022poster

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks not seen during training. Many promising approaches to this c…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2022

MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control

Nolan Wagener, Andrey Kolobov, Felipe Vieira Frujeri, Ricky Loynd, Ching-An Cheng, Matthew Hausknecht
NeurIPS 2022accept

Simulated humanoids are an appealing research domain due to their physical capabilities. Nonetheless, they are also challenging to control, as a policy must drive an unstable, discontinuous, and high-dimensional physical system. One widely studied approach is to utilize motion capture (MoCap) data t…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2020

MultiPoint: Cross-spectral registration of thermal and optical aerial imagery

Florian Achermann, Andrey Kolobov, Debadeepta Dey, Timo Hinzmann, Jen Jen Chung, Roland Siegwart +1
CoRL 2020

While optical cameras are ubiquitous in robotics, some robots can sense the world in several sections of the electromagnetic spectrum simultaneously, which can extend their capabilities in fundamental ways. For instance, many fixed-wing UAVs carry both optical and thermal imaging cameras, potentiall

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2020

Policy Improvement via Imitation of Multiple Oracles

Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
NeurIPS 2020spotlight

Despite its promise, reinforcement learning’s real-world adoption has been hampered by the need for costly exploration to learn a good policy. Imitation learning (IL) mitigates this shortcoming by using an oracle policy during training as a bootstrap to accelerate the learning process. However, in m…

Cited by 38Source ↗PDF ↗code ↗Scholar ↗
2020

Safe Reinforcement Learning via Curriculum Induction

Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal
NeurIPS 2020spotlight

In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing safe reinforcement learning methods make an agent rely on pri…

Cited by 119Source ↗PDF ↗code ↗Scholar ↗
2019

Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling

Andrey Kolobov, Yuval Peres, Cheng Lu, Eric J Horvitz
NeurIPS 2019poster

From traditional Web search engines to virtual assistants and Web accelerators, services that rely on online information need to continually keep track of remote content changes by explicitly requesting content updates from remote sources (e.g., web pages). We propose a novel optimization objective…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2018

ArduSoar: An Open-Source Thermalling Controller for Resource-Constrained Autopilots

Samuel Tabor, Iain Guilliard, Andrey Kolobov
IROS 2018poster

Autonomous soaring capability has the potential to significantly increase time aloft for fixed-wing UAVs. In this paper, we introduce ArduSoar, the first soaring controller integrated into a major autopilot software suite for small UAVs. We describe ArduSoar from the algorithmic standpoint, outline…

Cited by 23Source ↗Scholar ↗
2018

Autonomous Thermalling as a Partially Observable Markov Decision Process

Iain Guilliard, Rick Rogahn, Jim Piavi, Andrey Kolobov
RSS 2018poster

Small uninhabited aerial vehicles (sUAVs) commonly rely on active propulsion to stay airborne, which limits flight time and range. To address this, autonomous soaring seeks to utilize free atmospheric energy in the form of updrafts (thermals). However, their irregular nature at low altitudes makes t…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗