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

By Vlad Firoiu, William F. Whitney, Josh Tenenbaum. 2017

43 citations recorded by the source corpus.

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 methods on Super Smash Bros. Melee (SSBM), a popular console fighting game. The SSBM environment has complex dynamics and partial observability, making it challenging for human and machine alike. The multi-player aspect poses an additional challenge, as the vast majority of recent advances in RL have focused on single-agent environments. Nonetheless, we will show that it is possible to train agents that are competitive against and even surpass human professionals, a new result for the multi-player video game setting.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Unmasking Clever Hans predictors and assessing what machines really learn (2019, background): “They have scored commanding successes in the venues of strategic games [5,7, 58,79], image classification [78], face [80,81] recognition, speech recognition [82] and e.”
Evaluation and Design of Robust Neural Network Defenses (2018, background): “This includes the game of Go [118], Chess, and traditional video games [85, 28].”
Understanding and Comparing Deep Neural Networks for Age and Gender Classification (2017, background): “…learning to read subway plans [15], understanding quantum many-body systems [36], decoding human movement from EEG signals [40, 35] and matching or even exceeding human performance in playing games such as Go [37], Texas hold’em poker [29], various Atari 2600 games [25] or Super Smash Bros. [10].”