Reinforcement Learning

A Boolean Task Algebra for Reinforcement Learning

We propose a framework for defining a Boolean algebra over the space of tasks. This allows us to formulate new tasks in terms of the …

Geraud Nangue Tasse, Steven James, Benjamin Rosman

Combining Primitive DQNs for Improved Reinforcement Learning in Minecraft

We ask whether a reinforcement learning agent learns better by first learning the skills to perform smaller tasks in a complex …

Matthew Reynard, Herman Kamper, Herman A Engelbrecht, Benjamin Rosman

Learning Options from Demonstration using Skill Segmentation

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills …

Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod

Understanding Structure of Concurrent Actions

Whereas most work in reinforcement learning (RL) ignores the structure or relationships between actions, in this paper we show that …

Perusha Moodley, Benjamin Rosman, Xia Hong

Composing Value Functions in Reinforcement Learning

An important property for lifelong-learning agents is the ability to combine existing skills to solve new unseen tasks. In general, …

Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman

Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces

Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a …

Craig Bester, Steven James, George Konidaris

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a …

Ofir Marom, Benjamin Rosman

Learning to Plan with Portable Symbols

We present a framework for autonomously learning a portable symbolic representation that describes a collection of low-level continuous …

Steven James, Benjamin Rosman, George Konidaris

Will it Blend? Composing Value Functions in Reinforcement Learning

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, …

Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman

Hierarchical Subtask Discovery with Non-negative Matrix Factorization

Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, …

Adam Earle, Andrew Saxe, Benjamin Rosman