56 citations · 265 across the 35 of their papers we have counts for
12 papers · 1 filter
Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals
Sonny T. Jones, Grange M. Simpson, Patrick M. Pilarski +1
Rehabilitation technology is a natural setting to study the shared learning and decision-making of human and machine agents. In this work, we explore the use of Hierarchical Reinfo…
Continually Learned Pavlovian Signalling Without Forgetting for Human-in-the-Loop Robotic Control
Adam S. R. Parker, Michael R. Dawson, Patrick M. Pilarski
Artificial limbs are sophisticated devices to assist people with tasks of daily living. Despite advanced robotic prostheses demonstrating similar motion capabilities to biological…
What Should I Know? Using Meta-gradient Descent for Predictive Feature Discovery in a Single Stream of Experience
Alexandra Kearney, Anna Koop, Johannes Günther +1
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 en…
Prototyping three key properties of specific curiosity in computational reinforcement learning
Nadia M. Ady, Roshan Shariff, Johannes Günther +1
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 w…
Finding Useful Predictions by Meta-gradient Descent to Improve Decision-making
Alex Kearney, Anna Koop, Johannes Günther +1
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 fo…
Gamma-Nets: Generalizing Value Estimation over Timescale
Craig Sherstan, Shibhansh Dohare, James MacGlashan +2
We present -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…
Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures
Johannes Günther, Nadia M. Ady, Alex Kearney +2
Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitat…
Interpretable PID Parameter Tuning for Control Engineering using General Dynamic Neural Networks: An Extensive Comparison
Johannes Günther, Elias Reichensdörfer, Patrick M. Pilarski +1
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…
When is a Prediction Knowledge?
Alex Kearney, Patrick M. Pilarski
Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent's knowledge of the world through predictions about sensation, behavio…
Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning
Alex Kearney, Vivek Veeriah, Jaden Travnik +2
There is a long history of using meta learning as representation learning, specifically for determining the relevance of inputs. In this paper, we examine an instance of meta-learn…
TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent
Alex Kearney, Vivek Veeriah, Jaden B. Travnik +2
In this paper, we introduce a method for adapting the step-sizes of temporal difference (TD) learning. The performance of TD methods often depends on well chosen step-sizes, yet fe…
Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation
Craig Sherstan, Marlos C. Machado, Patrick M. Pilarski
Here we propose using the successor representation (SR) to accelerate learning in a constructive knowledge system based on general value functions (GVFs). In real-world settings li…