39 citations · 140 across the 12 of their papers we have counts for
14 papers
Variational Inference for Model-Free and Model-Based Reinforcement Learning
Felix Leibfried
Variational inference (VI) is a specific type of approximate Bayesian inference that approximates an intractable posterior distribution with a tractable one. VI casts the inference…
Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
John McLeod, Hrvoje Stojic, Vincent Adam +4
In the past decade, model-free reinforcement learning (RL) has provided solutions to challenging domains such as robotics. Model-based RL shows the prospect of being more sample-ef…
GPflux: A Library for Deep Gaussian Processes
Vincent Dutordoir, Hugh Salimbeni, Eric Hambro +7
We introduce GPflux, a Python library for Bayesian deep learning with a strong emphasis on deep Gaussian processes (DGPs). Implementing DGPs is a challenging endeavour due to the v…
A Tutorial on Sparse Gaussian Processes and Variational Inference
Felix Leibfried, Vincent Dutordoir, ST John +1
Gaussian processes (GPs) provide a framework for Bayesian inference that can offer principled uncertainty estimates for a large range of problems. For example, if we consider regre…
Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning
Felix Leibfried, Jordi Grau-Moya
Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent…
A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
Felix Leibfried, Sergio Pascual-Diaz, Jordi Grau-Moya
Empowerment is an information-theoretic method that can be used to intrinsically motivate learning agents. It attempts to maximize an agent's control over the environment by encour…
Uncertainty in Neural Networks: Approximately Bayesian Ensembling
Tim Pearce, Felix Leibfried, Alexandra Brintrup +2
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying…
Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks
Felix Leibfried, Peter Vrancx
This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yie…
An information-theoretic on-line update principle for perception-action coupling
Zhen Peng, Tim Genewein, Felix Leibfried +1
Inspired by findings of sensorimotor coupling in humans and animals, there has recently been a growing interest in the interaction between action and perception in robotic systems…
Balancing Two-Player Stochastic Games with Soft Q-Learning
Jordi Grau-Moya, Felix Leibfried, Haitham Bou-Ammar
Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision m…
An Information-Theoretic Optimality Principle for Deep Reinforcement Learning
Felix Leibfried, Jordi Grau-Moya, Haitham Bou-Ammar
We methodologically address the problem of Q-value overestimation in deep reinforcement learning to handle high-dimensional state spaces efficiently. By adapting concepts from info…
A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games
Felix Leibfried, Nate Kushman, Katja Hofmann
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approa…
Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes
Jordi Grau-Moya, Felix Leibfried, Tim Genewein +1
Information-theoretic principles for learning and acting have been proposed to solve particular classes of Markov Decision Problems. Mathematically, such approaches are governed by…
Bounded Rational Decision-Making in Feedforward Neural Networks
Felix Leibfried, Daniel Alexander Braun
Bounded rational decision-makers transform sensory input into motor output under limited computational resources. Mathematically, such decision-makers can be modeled as information…