David Szepesvari — accepted AI-conference papers

2024

Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint)

Richard S. Sutton, Marlos C. Machado, G. Zacharias Holland, David Szepesvari, Finbarr Timbers, Brian Tanner +1

AAAI 2024technical

To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction, but temporal abstraction has rarely been used, despite extensively developed t…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

When should agents explore?

Miruna Pislar, David Szepesvari, Georg Ostrovski, Diana L Borsa, Tom Schaul

ICLR 2022spotlight

Exploration remains a central challenge for reinforcement learning (RL). Virtually all existing methods share the feature of a *monolithic* behaviour policy that changes only gradually (at best). In contrast, the exploratory behaviours of animals and humans exhibit a rich diversity, namely including…

Cited by 39 Source ↗PDF ↗Scholar ↗

2016

Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

S. M. Ali Eslami, Nicolas Heess, Theophane Weber, Yuval Tassa, David Szepesvari, koray kavukcuoglu +1

NeurIPS 2016poster

We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurrent neural network that attends to scene elements and processes them one at a time. Crucially, the model itself learns t…

Cited by 634 Source ↗PDF ↗Scholar ↗