Superstition in the Network: Deep Reinforcement Learning Plays Deceptive Games

no code implementations • 12 Aug 2019 • Philip Bontrager, Ahmed Khalifa, Damien Anderson, Matthew Stephenson, Christoph Salge, Julian Togelius

Deep reinforcement learning has learned to play many games well, but failed on others.

reinforcement-learning Reinforcement Learning (RL)

Ensemble Decision Systems for General Video Game Playing

no code implementations • 26 May 2019 • Damien Anderson, Cristina Guerrero-Romero, Diego Perez-Liebana, Philip Rodgers, John Levine

Ensemble Decision Systems offer a unique form of decision making that allows a collection of algorithms to reason together about a problem.

Decision Making

A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking

1 code implementation • 9 Sep 2018 • Matthew Stephenson, Damien Anderson, Ahmed Khalifa, John Levine, Jochen Renz, Julian Togelius, Christoph Salge

This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms.

Benchmarking

Deceptive Games

no code implementations • 31 Jan 2018 • Damien Anderson, Matthew Stephenson, Julian Togelius, Christian Salge, John Levine, Jochen Renz

Deceptive games are games where the reward structure or other aspects of the game are designed to lead the agent away from a globally optimal policy.