18 citations · 43 across the 22 of their papers we have counts for
13 papers · 1 filter
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…
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…
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…
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…
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…
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…