We introduce a novel feature set for reinforcement learning in visual domains (e.g. video games) designed to capture pairwise, position-invariant, spatial relationships between objects on the screen. The feature set is simple to implement and computationally practical, but nevertheless allows for substantial improvement over existing baselines in a wide variety of Atari 2600 games. In the most ...

We introduce platform studies, a family of approaches to digital media. In platform studies, close consideration is given to the detailed technical workings of computing systems. This allows the connections between platform technologies and creative production to be investigated. Two short studies of the Atari VCS (2600) and the Nintendo Wii show how close consideration of this sort can inform ...

Computer simulation approaches are starting to be used more extensively throughout scientific investigations. Some scientists, however, are skeptical about the benefits of simulation. We present computer simulation as a scientific instrument in order to explore issues of their construction and use, which we believe might increase their acceptance within science. We highlight the need to underst...

Fractal AI is a theory for general artificial intelligence. It allows to derive new mathematical tools that constitute the foundations for a new kind of stochastic calculus, by modelling information using cellular automaton-like structures instead of smooth functions. In the repository included we are presenting a new Agent, derived from the first principles of the theory, which is capable of s...

The Atari 2600 games supported in the Arcade Learning Environment [Bellemare et al., 2013] all feature a known initial (RAM) state and actions that have deterministic effects. Classical planners, however, cannot be used off-the-shelf as there is no compact PDDL-model of the games, and action effects and goals are not known a priori. Indeed, there are no explicit goals, and the planner must sele...

The efficiency of reinforcement learning algorithms depends critically on a few metaparameters that modulates the learning updates and the trade-off between exploration and exploitation. The adaptation of the meta-parameters is an open question in reinforcement learning, which arguably has become more of an issue recently with the success of deep reinforcement learning in high-dimensional state...

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experienc...