Nintendo Super Smash Bros. Melee: An "Untouchable" Agent

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of RL tasks, from Atari games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning, that learn to play from experience with minimal knowledge of the specific domain of interest. In this work, we will investigate the performance of these me...

Deep In-GPU Experience Replay

Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copi...

Playing with the Rules: Social and Cultural Aspects of Game Rules in a Console Game Club

In this study of a Swedish console game club I have looked at how the rules of the games are connected to the social and cultural aspects of the context that the games are played in. I have devoted special attention to the game Super Smash Bros. Melee and how different contexts of play have formed around this game, for instance the emergence of a professional smash scene and the polarization of...

Nintendo’s Legacy of Sequel Supremacy: A Case Study of Super Smash Bros

Principles of DC and RF Linear 11 Accelerators

Ancient Greeks and Indians had the conception of atoms. They thought and debated in great lengths about the fundamental constituents of matter. They were limited in what they can do, besides talking, due to the paucity of Particle Accelarators. In the last few decades, this has been rectified. We have many particle accelerators. Particle accelerators are what Feynman described as smashing swiss...