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

02/21/2017

∙

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.

READ FULL TEXT

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

At Human Speed: Deep Reinforcement Learning with Action Delay

Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting

Phoenix: A Self-Optimizing Chess Engine

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

Related Research

At Human Speed: Deep Reinforcement Learning with Action Delay

Human-level performance in first-person multiplayer games with population-based deep reinforcement learning

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Learning to Play No-Press Diplomacy with Best Response Policy Iteration

Deep Pepper: Expert Iteration based Chess agent in the Reinforcement Learning Setting

Phoenix: A Self-Optimizing Chess Engine