Accelerating Empowerment Computation with UCT Tree Search
This work addresses a bottleneck for researchers and developers using empowerment in applications like video games, though it is incremental as it builds on existing UCT methods.
The paper tackles the computational expense of empowerment in intrinsic motivation models by proposing a modified UCT tree search method for discrete and deterministic scenarios, demonstrating that it achieves close to exhaustive computation baselines with reduced resources.
Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from intrinsically motivated general game-playing agents to non-player characters such as companions and enemies. The information-theoretic quantity of Empowerment is a particularly promising candidate motivation to produce believable, generic and robust behaviour. However, while it can be used in the absence of external reward functions that would need to be crafted and learned, empowerment is computationally expensive. In this paper, we propose a modified UCT tree search method to mitigate empowerment's computational complexity in discrete and deterministic scenarios. We demonstrate how to modify a Monte-Carlo Search Tree with UCT to realise empowerment maximisation, and discuss three additional modifications that facilitate better sampling. We evaluate the approach both quantitatively, by analysing how close our approach gets to the baseline of exhaustive empowerment computation with varying amounts of computational resources, and qualitatively, by analysing the resulting behaviour in a Minecraft-like scenario.