AIConfPaper
← Search

Boris Belousov

17 accepted papers

2026

Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd “AI Olympics with RealAIGym” Competition

Felix Wiebe, Niccolò Turcato, Alberto Dalla Libera, Jean Seong Bjorn Choe, Bumkyu Choi, Tim Faust +15
ICRA 2026poster

In robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and …

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning

Théo Vincent, Fabian Wahren, Jan Peters, Boris Belousov, Carlo D'Eramo
ICLR 2025poster

Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand. This also limits the applicability of RL in real-world scenarios. In recent years, the field of automated Reinforcement…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis

Erik Helmut, Luca Dziarski, Niklas Funk, Boris Belousov, Jan Peters
IROS 2025

Contact-rich manipulation remains a major challenge in robotics. Optical tactile sensors like GelSight Mini offer a low-cost solution for contact sensing by capturing softbody deformations of the silicone gel. However, accurately inferring shear and normal force distributions from these gel deformat

Cited by 8Source ↗code ↗Scholar ↗
2024

CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity

Aditya Bhatt, Daniel Palenicek, Boris Belousov, Max Argus, Artemij Amiranashvili, Thomas Brox +1
ICLR 2024spotlight

Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the critic per environment sample. However, this comes at the expe…

Cited by 36Source ↗PDF ↗code ↗Scholar ↗
2024

Parameterized Projected Bellman Operator

Théo Vincent, Alberto Maria Metelli, Boris Belousov, Jan Peters, Marcello Restelli, Carlo D'Eramo
AAAI 2024technical

Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an iterated procedure where each step consists of (i) an application of the Bellman operator and (ii) a…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Reinforcement Learning for Athletic Intelligence: Lessons from the 1st “AI Olympics with RealAIGym” Competition

Felix Wiebe, Niccolò Turcato, Alberto Dalla Libera, Chi Zhang, Theo Vincent, Shubham Vyas +9
IJCAI 2024poster

As artificial intelligence gains new capabilities, it becomes important to evaluate it on real-world tasks. In particular, the fields of robotics and reinforcement learning (RL) are lacking in standardized benchmarking tasks on real hardware. To facilitate reproducibility and stimulate algorithmi…

Cited by 11Source ↗PDF ↗Scholar ↗
2024

What Matters for Active Texture Recognition With Vision-Based Tactile Sensors

Alina Böhm, Tim Schneider, Boris Belousov, Alap Kshirsagar, Lisa Lin, Katja Doerschner +3
ICRA 2024poster

This paper explores active sensing strategies that employ vision-based tactile sensors for robotic perception and classification of fabric textures. We formalize the active sampling problem in the context of tactile fabric recognition and provide an implementation of information-theoretic exploratio…

Cited by 7Source ↗Scholar ↗
2022

Active Exploration for Robotic Manipulation

Tim Schneider, Boris Belousov, Georgia Chalvatzaki, Diego Romeres, Devesh K. Jha, Jan Peters
IROS 2022poster

Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years. One of the key challenges in manipulation is the exploration of the dynamics of the environment when there is continuous contact between the objects being manipula…

Cited by 12Source ↗Scholar ↗
2021

Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction

Niklas Funk, Georgia Chalvatzaki, Boris Belousov, Jan Peters
CoRL 2021poster

Autonomous robotic assembly requires a well-orchestrated sequence of high-level actions and smooth manipulation executions. Learning to assemble complex 3D structures remains a challenging problem that requires drawing connections between target designs and building blocks, and creating valid assemb…

Cited by 56Source ↗Scholar ↗
2021

Neural Posterior Domain Randomization

Fabio Muratore, Theo Gruner, Florian Wiese, Boris Belousov, Michael Gienger, Jan Peters
CoRL 2021poster

Combining domain randomization and reinforcement learning is a widely used approach to obtain control policies that can bridge the gap between simulation and reality. However, existing methods make limiting assumptions on the form of the domain parameter distribution which prevents them from utilizi…

Cited by 46Source ↗Scholar ↗
2020

Underactuated Waypoint Trajectory Optimization for Light Painting Photography

Christian Eilers, Jonas Eschmann, Robin Menzenbach, Boris Belousov, Fabio Muratore, Jan Peters
ICRA 2020poster

Despite their abundance in robotics and nature, underactuated systems remain a challenge for control engineering. Trajectory optimization provides a generally applicable solution, however its efficiency strongly depends on the skill of the engineer to frame the problem in an optimizer-friendly way.…

Cited by 7Source ↗Scholar ↗
2019

HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints

Michael Lutter, Boris Belousov, Kim Listmann, Debora Clever, Jan Peters
CoRL 2019

Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an o

Cited by 0Source ↗PDF ↗Scholar ↗
2016

Catching heuristics are optimal control policies

Boris Belousov, Gerhard Neumann, Constantin A Rothkopf, Jan R Peters
NeurIPS 2016poster

Two seemingly contradictory theories attempt to explain how humans move to intercept an airborne ball. One theory posits that humans predict the ball trajectory to optimally plan future actions; the other claims that, instead of performing such complicated computations, humans employ heuristics to r…

Cited by 44Source ↗PDF ↗Scholar ↗