Agent X: Improving Exploration vs Exploitation in the State of the Art Angry Birds AI
Daniel Lutalo · 2022
AI agents have successfully employed deep reinforcement learning methods to surpass human performance in various new tasks over the past decade, notably including the domain of games. However, Angry Birds requires complex physical and spacial reasoning that is yet to be captured by such means. We present our logic-based Angry Birds AI which won the 2021 IJCAI AIBIRDS competition and propose a simple new method we call Second Order Thompson Sampling (SOTS) which allows for fine-tuning the balance between exploration and exploitation. We cover the competition scores of our entrant Agent X, its predecessor - the former state of the art Bambirds 2019, and the new and improved Bambirds 2021. We find that our agent has the best all-round performance, but would gain a lot by incorporating the improvements of Bambirds 2021. We list other potential areas of improvement for a future superhuman Angry Birds AI.