SC²S Colloquium - July 20, 2017

Date:	July 20, 2017
Room:	02.07.023
Time:	16:00 pm, s.t.

Ivan Mauricio Rodriguez: Deep Reinforcement Learning for Superhuman Performance in Doom

Over the last years, Reinforcement Learning (RL) has attracted the attention of many researchers. Its powerful combination with Artificial Deep Neural Networks, when used as function approximators, has shown to be successful in many works. Rather than target classical RL problems, the most prominent examples of these works develop techniques that allow agents to learn how to play video and board games from raw input data at human level. In this thesis, we describe the implementation of an algorithm to train an agent for the popular 90's computer game Doom. Doom features several recurrent problems in RL such as delayed rewards and partial observability which are tackled by the algorithm. In particular, we discuss the efforts to improve the efficiency of our approach and the results obtained in several tests scenarios.