Shaping Mario with Human Advice (Demonstration)
|Title||Shaping Mario with Human Advice (Demonstration)|
|Publication Type||Conference Paper|
|Year of Publication||2015|
|Authors||Harutyunyan, A, Brys, T, Vrancx, P, Nowe, A|
|Conference Name||International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS-15)|
In this demonstration, we allow humans to interactively advise a Mario agent during learning, and observe the resulting changes in performance, as compared to its unadvised counterpart. We do this via a novel potential-based reward shaping framework, capable for the first time of handling the scenario of online feedback.