Search Results for author: Johannes Günther

Found 8 papers, 0 papers with code

Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

no code implementations1 Dec 2022 Nadia M. Ady, Roshan Shariff, Johannes Günther, Patrick M. Pilarski

As a second main contribution of this work, we show how these properties may be implemented together in a proof-of-concept reinforcement learning agent: we demonstrate how the properties manifest in the behaviour of this agent in a simple non-episodic grid-world environment that includes curiosity-inducing locations and induced targets of curiosity.

Decision Making reinforcement-learning +1

What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience

no code implementations13 Jun 2022 Alexandra Kearney, Anna Koop, Johannes Günther, Patrick M. Pilarski

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features to enable better goal-directed decision-making.

Continual Learning Decision Making

Finding Useful Predictions by Meta-gradient Descent to Improve Decision-making

no code implementations18 Nov 2021 Alex Kearney, Anna Koop, Johannes Günther, Patrick M. Pilarski

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations.

Decision Making

Affordance as general value function: A computational model

no code implementations27 Oct 2020 Daniel Graves, Johannes Günther, Jun Luo

General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment.

Autonomous Driving Reinforcement Learning (RL)

Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures

no code implementations15 Aug 2019 Johannes Günther, Nadia M. Ady, Alex Kearney, Michael R. Dawson, Patrick M. Pilarski

Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitation.

Representation Learning

Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison

no code implementations30 May 2019 Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski, Klaus Diepold

In this paper, we examine the utility of extending PID controllers with recurrent neural networks-namely, General Dynamic Neural Networks (GDNN); we show that GDNN (neural) PID controllers perform well on a range of control systems and highlight how they can be a scalable and interpretable option for control systems.

Cannot find the paper you are looking for? You can Submit a new open access paper.