12 citations · 42 across the 21 of their papers we have counts for
23 papers
Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning
Mingyeong Kim, Gyusang Cho, Juho Lee +1
Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, makin…
LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors
Loukas Kordos, Leonard T. Franz, Simon Rappenecker +4
Learning-based quadrupedal locomotion typically relies on complex reward formulations that entangle task specification, operational limits, gait preference, and terrain adaptation…
GASP: Guided Asymmetric Self-Play For Coding LLMs
Swadesh Jana, Cansu Sancaktar, Tomáš Daniš +3
Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge…
Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning
Nikola Milosevic, Leonard Franz, Daniel Haeufle +3
We propose stochastic decision horizons (SDH), a theoretically grounded framework for survival-based constrained reinforcement learning from per-step violation signals. Rather than…
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models
Cansu Sancaktar, Christian Gumbsch, Andrii Zadaianchuk +2
Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approache…
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
Pavel Kolev, Marin Vlastelica, Georg Martius
Offline diversity maximization under imitation constraints can transform demonstration data into a set of distinct behavioral policies, improving robustness to distribution shift w…
Learning Diverse Skills for Local Navigation under Multi-constraint Optimality
Jin Cheng, Marin Vlastelica, Pavel Kolev +2
Despite many successful applications of data-driven control in robotics, extracting meaningful diverse behaviors remains a challenge. Typically, task performance needs to be compro…
Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World
Nico Gürtler, Felix Widmaier, Cansu Sancaktar +21
Experimentation on real robots is demanding in terms of time and costs. For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and be…
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
Nico Gürtler, Sebastian Blaes, Pavel Kolev +5
Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular…
Offline Diversity Maximization Under Imitation Constraints
Marin Vlastelica, Jin Cheng, Georg Martius +1
There has been significant recent progress in the area of unsupervised skill discovery, utilizing various information-theoretic objectives as measures of diversity. Despite these a…
On Imitation in Mean-field Games
Giorgia Ramponi, Pavel Kolev, Olivier Pietquin +3
We explore the problem of imitation learning (IL) in the context of mean-field games (MFGs), where the goal is to imitate the behavior of a population of agents following a Nash eq…
Online Learning under Adversarial Nonlinear Constraints
Pavel Kolev, Georg Martius, Michael Muehlebach
In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an algorith…
Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions
Chenhao Li, Sebastian Blaes, Pavel Kolev +3
Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly lab…
Physarum-Inspired Multi-Commodity Flow Dynamics
Vincenzo Bonifaci, Enrico Facca, Frederic Folz +6
In wet-lab experiments, the slime mold Physarum polycephalum has demonstrated its ability to solve shortest path problems and to design efficient networks. For the shortest path pr…
Secretary and Online Matching Problems with Machine Learned Advice
Antonios Antoniadis, Themis Gouleakis, Pieter Kleer +1
The classical analysis of online algorithms, due to its worst-case nature, can be quite pessimistic when the input instance at hand is far from worst-case. Often this is not an iss…
Convergence of the Non-Uniform Directed Physarum Model
Enrico Facca, Andreas Karrenbauer, Pavel Kolev +1
The directed Physarum dynamics is known to solve positive linear programs: minimize subject to and for a positive cost vector . The directed Physarum…
Convergence of the Non-Uniform Physarum Dynamics
Andreas Karrenbauer, Pavel Kolev, Kurt Mehlhorn
Let , , and . We show under fairly general conditions that the non-uniform Physarum dynamics \[ \dot{x}_…
A PTAS for -Low Rank Approximation
Frank Ban, Vijay Bhattiprolu, Karl Bringmann +3
A number of recent works have studied algorithms for entrywise -low rank approximation, namely, algorithms which given an matrix (with ), output…
Approximation Algorithms for -Low Rank Approximation
Karl Bringmann, Pavel Kolev, David P. Woodruff
We study the -Low Rank Approximation Problem, where the goal is, given an matrix , to output a rank- matrix for which is minimized. Her…
Two Results on Slime Mold Computations
Ruben Becker, Vincenzo Bonifaci, Andreas Karrenbauer +2
We present two results on slime mold computations. In wet-lab experiments (Nature'00) by Nakagaki et al. the slime mold Physarum polycephalum demonstrated its ability to solve shor…
Density Independent Algorithms for Sparsifying -Step Random Walks
Gorav Jindal, Pavel Kolev, Richard Peng +1
We give faster algorithms for producing sparse approximations of the transition matrices of -step random walks on undirected, weighted graphs. These transition matrices also for…
Approximate Spectral Clustering: Efficiency and Guarantees
Pavel Kolev, Kurt Mehlhorn
Approximate Spectral Clustering (ASC) is a popular and successful heuristic for partitioning the nodes of a graph into clusters for which the ratio of outside connections compa…
An Efficient Parallel Algorithm for Spectral Sparsification of Laplacian and SDDM Matrix Polynomials
Gorav Jindal, Pavel Kolev
For "large" class of continuous probability density functions (p.d.f.), we demonstrate that for every there is mixture of discrete Binomial distribu…