Clement Gehring
YOU?
Author Swipe
View article: Functional Risk Minimization
Functional Risk Minimization Open
The field of Machine Learning has changed significantly since the 1970s. However, its most basic principle, Empirical Risk Minimization (ERM), remains unchanged. We propose Functional Risk Minimization~(FRM), a general framework where loss…
View article: Neural differential equations for temperature control in buildings under demand response programs
Neural differential equations for temperature control in buildings under demand response programs Open
Heating Ventilation and Air Conditioning (HVAC) are energy-intensive systems that greatly contribute to peak demand, which can cause stability and reliability issues in the grid. The use of adaptive smart temperature controllers combined w…
View article: Do Transformer World Models Give Better Policy Gradients?
Do Transformer World Models Give Better Policy Gradients? Open
A natural approach for reinforcement learning is to predict future rewards by unrolling a neural network world model, and to backpropagate through the resulting computational graph to learn a policy. However, this method often becomes impr…
View article: Bridging State and History Representations: Understanding Self-Predictive RL
Bridging State and History Representations: Understanding Self-Predictive RL Open
Representations are at the core of all deep reinforcement learning (RL) methods for both Markov decision processes (MDPs) and partially observable Markov decision processes (POMDPs). Many representation learning methods and theoretical fra…
View article: Course Correcting Koopman Representations
Course Correcting Koopman Representations Open
Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space. Theoretically, such features can be used to simplify many problems in modeling and control of NLDS. In t…
View article: Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators Open
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems fou…
View article: Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators Open
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems fou…
View article: Robust Reinforcement Learning: A Constrained Game-theoretic Approach
Robust Reinforcement Learning: A Constrained Game-theoretic Approach Open
Deep reinforcement learning (RL) methods provide state-of-art performance in complex control tasks. However, it has been widely recognized that RL methods often fail to generalize due to unaccounted uncertainties. In this work, we propose …
View article: Comment on “Giant electromechanical coupling of relaxor ferroelectrics controlled by polar nanoregion vibrations”
Comment on “Giant electromechanical coupling of relaxor ferroelectrics controlled by polar nanoregion vibrations” Open
Phantom indications of phonon anticrossing in relaxor ferroelectrics can arise via an inelastic double-scattering process.
View article: Batched Large-scale Bayesian Optimization in High-dimensional Spaces
Batched Large-scale Bayesian Optimization in High-dimensional Spaces Open
Bayesian optimization (BO) has become an effective approach for black-box function optimization problems when function evaluations are expensive and the optimum can be achieved within a relatively small number of queries. However, many cas…