Shaping Mario with Human Advice
Anna Harutyunyan, Tim Brys, Peter Vrancx, Ann Nowé · Adaptive Agents and Multi-Agents Systems · 2015
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.