18 citations · 43 across the 22 of their papers we have counts for
24 papers
Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo
Lohithsai Yadala Chanchu, Hany Abdulsamad, Christian A. Naesseth
We study inference-time control for text generation in discrete diffusion language models, where the goal is to steer sampling toward sequence-level rewards without retraining. Pri…
Maximin Robust Bayesian Experimental Design
Hany Abdulsamad, Sahel Iqbal, Christian A. Naesseth +2
We address the brittleness of Bayesian experimental design under model misspecification by formulating the problem as a max--min game between the experimenter and an adversarial na…
Recursive Entropic Variational Inference for Nonlinear State-Space Models
Hany Abdulsamad, Ángel F. García-Fernández, Simo Särkkä
We present a class of algorithms for state estimation in nonlinear, non-Gaussian state-space models. Our approach is based on a variational Lagrangian formulation that casts Bayesi…
Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
Hany Abdulsamad, Sahel Iqbal, Simo Särkkä
Optimal decision-making under partial observability requires agents to balance reducing uncertainty (exploration) against pursuing immediate objectives (exploitation). In this pape…
A Parallel-in-Time Newton's Method for Nonlinear Model Predictive Control
Casian Iacob, Hany Abdulsamad, Simo Särkkä
Model predictive control (MPC) is a powerful framework for optimal control of dynamical systems. However, MPC solvers suffer from a high computational burden that restricts their a…
Recursive Nested Filtering for Efficient Amortized Bayesian Experimental Design
Sahel Iqbal, Hany Abdulsamad, Sara Pérez-Vieites +2
This paper introduces the Inside-Out Nested Particle Filter (IO-NPF), a novel, fully recursive, algorithm for amortized sequential Bayesian experimental design in the non-exchangea…
Nesting Particle Filters for Experimental Design in Dynamical Systems
Sahel Iqbal, Adrien Corenflos, Simo Särkkä +1
In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside…
Risk-Sensitive Stochastic Optimal Control as Rao-Blackwellized Markovian Score Climbing
Hany Abdulsamad, Sahel Iqbal, Adrien Corenflos +1
Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, provi…
A Recursive Newton Method for Smoothing in Nonlinear State Space Models
Fatemeh Yaghoobi, Hany Abdulsamad, Simo Särkkä
In this paper, we use the optimization formulation of nonlinear Kalman filtering and smoothing problems to develop second-order variants of iterated Kalman smoother (IKS) methods.…
Variational Gaussian filtering via Wasserstein gradient flows
Adrien Corenflos, Hany Abdulsamad
We present a novel approach to approximate Gaussian and mixture-of-Gaussians filtering. Our method relies on a variational approximation via a gradient-flow representation. The gra…
Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics
Hany Abdulsamad, Peter Nickl, Pascal Klink +1
Well-calibrated probabilistic regression models are a crucial learning component in robotics applications as datasets grow rapidly and tasks become more complex. Unfortunately, cla…
Active Inference for Robotic Manipulation
Tim Schneider, Boris Belousov, Hany Abdulsamad +1
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades. One of the central challenges of manipu…
Model-Based Reinforcement Learning via Stochastic Hybrid Models
Hany Abdulsamad, Jan Peters
Optimal control of general nonlinear systems is a central challenge in automation. Enabled by powerful function approximators, data-driven approaches to control have recently succe…
Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference
Joe Watson, Hany Abdulsamad, Rolf Findeisen +1
Optimal control under uncertainty is a prevailing challenge for many reasons. One of the critical difficulties lies in producing tractable solutions for the underlying stochastic o…
Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions
Hany Abdulsamad, Tim Dorau, Boris Belousov +2
Trajectory optimization and model predictive control are essential techniques underpinning advanced robotic applications, ranging from autonomous driving to full-body humanoid cont…
A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning
Pascal Klink, Hany Abdulsamad, Boris Belousov +3
Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives. For reinforcement…
A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning
Hany Abdulsamad, Peter Nickl, Pascal Klink +1
Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to hi…
Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation
Hany Abdulsamad, Jan Peters
The control of nonlinear dynamical systems remains a major challenge for autonomous agents. Current trends in reinforcement learning (RL) focus on complex representations of dynami…
A Nonparametric Off-Policy Policy Gradient
Samuele Tosatto, Joao Carvalho, Hany Abdulsamad +1
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is es…
Receding Horizon Curiosity
Matthias Schultheis, Boris Belousov, Hany Abdulsamad +1
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatme…
Self-Paced Contextual Reinforcement Learning
Pascal Klink, Hany Abdulsamad, Boris Belousov +1
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a p…
Stochastic Optimal Control as Approximate Input Inference
Joe Watson, Hany Abdulsamad, Jan Peters
Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the…
Chance-Constrained Trajectory Optimization for Non-linear Systems with Unknown Stochastic Dynamics
Onur Celik, Hany Abdulsamad, Jan Peters
Iterative trajectory optimization techniques for non-linear dynamical systems are among the most powerful and sample-efficient methods of model-based reinforcement learning and app…
Model-Free Trajectory-based Policy Optimization with Monotonic Improvement
Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad +2
Many of the recent trajectory optimization algorithms alternate between linear approximation of the system dynamics around the mean trajectory and conservative policy update. One w…