arXiv subjects

Johannes Günther

Publications and source records attributed to Johannes Günther.

11 recordsLinked to original sources

arXiv2026

Coachable agents for interactive gameplay

Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior to solve their tasks. However, there are many use cases in which one would like to assert some level of control, preferably in real time, over how the task is solved. We refer to these modifications of a core task as styles. We combine universal value function approximators (UVFAs) with carefully selected training scenarios, learning algorithms, and data augmentation to create a framework for coaching agents that exhibit styles in complex domains. We demonstrate the framework's application in the AAA video games Horizon Forbidden West and Gran Turismo, and in an open-source humanoid test domain. Despite the different nature of the domains -- car racing, stylized game combat, and humanoid walking -- each agent shows strong coherence to the style requests while still satisfying the main task in its domain. Importantly, the techniques outlined in this paper allow an end user to choose the final behavior at run time, giving them flexible control over the final executed performance.

cs.AI↗

arXiv2023

Scalable Ray Tracing Using the Distributed FrameBuffer

Image- and data-parallel rendering across multiple nodes on high-performance computing systems is widely used in visualization to provide higher frame rates, support large data sets, and render data in situ. Specifically for in situ visualization, reducing bottlenecks incurred by the visualization and compositing is of key concern to reduce the overall simulation runtime. Moreover, prior algorithms have been designed to support either image- or data-parallel rendering and impose restrictions on the data distribution, requiring different implementations for each configuration. In this paper, we introduce the Distributed FrameBuffer, an asynchronous image-processing framework for multi-node rendering. We demonstrate that our approach achieves performance superior to the state of the art for common use cases, while providing the flexibility to support a wide range of parallel rendering algorithms and data distributions. By building on this framework, we extend the open-source ray tracing library OSPRay with a data-distributed API, enabling its use in data-distributed and in situ visualization applications.

cs.GR↗

arXiv2022

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

Curiosity for machine agents has been a focus of lively research activity. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we conduct a comprehensive, multidisciplinary survey of the field of animal and machine curiosity. As a principal contribution of this work, we use this survey as a foundation to introduce and define what we consider to be five of the most important properties of specific curiosity: 1) directedness towards inostensible referents, 2) cessation when satisfied, 3) voluntary exposure, 4) transience, and 5) coherent long-term learning. 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. As we would hope, our example of a computational specific curiosity agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work, therefore, presents a landmark synthesis and translation of specific curiosity to the domain of machine learning and reinforcement learning and provides a novel view into how specific curiosity operates and in the future might be integrated into the behaviour of goal-seeking, decision-making computational agents in complex environments.

cs.AI↗

arXiv2022

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

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. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. This challenge is especially apparent in continual learning problems where a single stream of experience is available to a singular agent. As a primary contribution, we introduce a meta-gradient descent process by which an agent learns 1) what predictions to make, 2) the estimates for its chosen predictions, and 3) how to use those estimates to generate policies that maximize future reward -- all during a single ongoing process of continual learning. In this manuscript we consider predictions expressed as General Value Functions: temporally extended estimates of the accumulation of a future signal. We demonstrate that through interaction with the environment an agent can independently select predictions that resolve partial-observability, resulting in performance similar to expertly specified GVFs. By learning, rather than manually specifying these predictions, we enable the agent to identify useful predictions in a self-supervised manner, taking a step towards truly autonomous systems.

cs.LG↗

arXiv2022

Prototyping three key properties of specific curiosity in computational reinforcement learning

Curiosity for machine agents has been a focus of intense research. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we introduce three of the most immediate of these properties -- directedness, cessation when satisfied, and voluntary exposure -- and show how they may be implemented together in a proof-of-concept reinforcement learning agent; further, 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. As we would hope, the agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work therefore presents a novel view into how specific curiosity operates and in the future might be integrated into the behaviour of goal-seeking, decision-making agents in complex environments.

cs.LG↗

arXiv2021

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

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions: temporally extended estimates of the accumulation of a future signal. One challenge is determining from the infinitely many predictions that the agent could possibly make which might support decision-making. In this work, we contribute a meta-gradient descent method by which an agent can directly specify what predictions it learns, independent of designer instruction. To that end, we introduce a partially observable domain suited to this investigation. We then demonstrate that through interaction with the environment an agent can independently select predictions that resolve the partial-observability, resulting in performance similar to expertly chosen value functions. By learning, rather than manually specifying these predictions, we enable the agent to identify useful predictions in a self-supervised manner, taking a step towards truly autonomous systems.

cs.LG↗

arXiv2021

Affordance as general value function: A computational model

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. Affordances as perceived action possibilities with specific valence may be cast into predicted policy-relative goodness and modelled as GVFs. A systematic explication of this connection shows that GVFs and especially their deep learning embodiments (1) realize affordance prediction as a form of direct perception, (2) illuminate the fundamental connection between action and perception in affordance, and (3) offer a scalable way to learn affordances using RL methods. Through an extensive review of existing literature on GVF applications and representative affordance research in robotics, we demonstrate that GVFs provide the right framework for learning affordances in real-world applications. In addition, we highlight a few new avenues of research opened up by the perspective of "affordance as GVF", including using GVFs for orchestrating complex behaviors.

cs.AI↗

arXiv2020

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

Modern automation systems rely on closed loop control, wherein a controller interacts with a controlled process, based on observations. These systems are increasingly complex, yet most controllers are linear Proportional-Integral-Derivative (PID) controllers. PID controllers perform well on linear and near-linear systems but their simplicity is at odds with the robustness required to reliably control complex processes. Modern machine learning offers a way to extend PID controllers beyond their linear capabilities by using neural networks. However, such an extension comes at the cost of losing stability guarantees and controller interpretability. 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. To do so, we provide an extensive study using four benchmark systems that represent the most common control engineering benchmarks. All control benchmarks are evaluated with and without noise as well as with and without disturbances. The neural PID controller performs better than standard PID control in 15 of 16 tasks and better than model-based control in 13 of 16 tasks. As a second contribution, we address the lack of interpretability that prevents neural networks from being used in real-world control processes. We use bounded-input bounded-output stability analysis to evaluate the parameters suggested by the neural network, thus making them understandable. This combination of rigorous evaluation paired with better interpretability is an important step towards the acceptance of neural-network-based control approaches. It is furthermore an important step towards interpretable and safely applied artificial intelligence.

cs.LG↗

arXiv2020

Gamma-Nets: Generalizing Value Estimation over Timescale

We present $Γ$-nets, a method for generalizing value function estimation over timescale. By using the timescale as one of the estimator's inputs we can estimate value for arbitrary timescales. As a result, the prediction target for any timescale is available and we are free to train on multiple timescales at each timestep. Here we empirically evaluate $Γ$-nets in the policy evaluation setting. We first demonstrate the approach on a square wave and then on a robot arm using linear function approximation. Next, we consider the deep reinforcement learning setting using several Atari video games. Our results show that $Γ$-nets can be effective for predicting arbitrary timescales, with only a small cost in accuracy as compared to learning estimators for fixed timescales. $Γ$-nets provide a method for compactly making predictions at many timescales without requiring a priori knowledge of the task, making it a valuable contribution to ongoing work on model-based planning, representation learning, and lifelong learning algorithms.

cs.LG↗

arXiv2020

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

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. A property that makes these predictive approaches well suited for robotics is that they can be learned online and incrementally through interaction with the environment. However, a remaining challenge for many prediction-learning approaches is an appropriate choice of prediction-learning parameters, especially parameters that control the magnitude of a learning machine's updates to its predictions (the learning rate or step size). To begin to address this challenge, we examine the use of online step-size adaptation using a sensor-rich robotic arm. Our method of choice, Temporal-Difference Incremental Delta-Bar-Delta (TIDBD), learns and adapts step sizes on a feature level; importantly, TIDBD allows step-size tuning and representation learning to occur at the same time. We show that TIDBD is a practical alternative for classic Temporal-Difference (TD) learning via an extensive parameter search. Both approaches perform comparably in terms of predicting future aspects of a robotic data stream. Furthermore, the use of a step-size adaptation method like TIDBD appears to allow a system to automatically detect and characterize common sensor failures in a robotic application. Together, these results promise to improve the ability of robotic devices to learn from interactions with their environments in a robust way, providing key capabilities for autonomous agents and robots.

cs.LG↗

arXiv2019

Visualizing the world's largest turbulence simulation

In this exploratory submission we present the visualization of the largest interstellar turbulence simulations ever performed, unravelling key astrophysical processes concerning the formation of stars and the relative role of magnetic fields. The simulations, including pure hydrodynamical (HD) and magneto-hydrodynamical (MHD) runs, up to a size of $10048^3$ grid elements, were produced on the supercomputers of the Leibniz Supercomputing Centre and visualized using the hybrid parallel (MPI+TBB) ray-tracing engine OSPRay associated with VisIt. Besides revealing features of turbulence with an unprecedented resolution, the visualizations brilliantly showcase the stretching-and-folding mechanisms through which astrophysical processes such as supernova explosions drive turbulence and amplify the magnetic field in the interstellar gas, and how the first structures, the seeds of newborn stars are shaped by this process.

physics.comp-ph↗