We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
A newly designed game is introduced, which feels like Backgammon, but has a simplified rule set. Unlike earlier attempts at simplifying the game, Nannon maintains enough features a...
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
Designing agents whose behavior challenges human players adequately is a key issue in computer games development. This work presents a novel technique, based on reinforcement lear...
Gustavo Andrade, Geber Ramalho, Hugo Santana, Vinc...