HackerPapers

arXiv:1702.06230cs.LG

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

Vlad Firoiu, William F. Whitney, Joshua B. Tenenbaum

Abstract

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.

arXiv comments
Journal reference
DOI
Subjects
cs.LGMachine Learning cs.AIArtificial Intelligence

On Hacker News

Linked by 5 identifiable commenters in 5 comments across 5 threads, from Apr 2017 to Jul 2018. Found in 1 HN submission from Feb 2017 to Feb 2017. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments5 threads

  1. OpenAI Five Benchmark 1 comment

    • > We’ve increased the reaction time of OpenAI Five from 80ms to 200ms. This reaction time is much closer to human level, though we haven’t seen evidence of changes in gameplay as Openai Five’s strength comes more from teamwork and coordination than reflexes. This new constraint…

      minimaxirView on HNParent context

  2. Super Smash Bros. Melee: An “Untouchable” Agent 1 comment

    • I was pretty impressed by the Falcon AI earlier this year. He actually used modern reinforcement learning to train from 0 instead of the crappy built in AI. Also, his AI was limited to near-human reaction time (10 frames) which led to a more human-looking agent. At the end of…

      chisView on HNParent context

  3. Competitive Self-Play 1 comment

    • > As far as I know, elite human players are still massively dominant. I wouldn't be so sure: https://arxiv.org/abs/1702.06230

      canjobearView on HNParent context

  4. Street Fighter II's AI Engine 1 comment

    • > I wonder if knowing the different strategies would make pro-humans better at playing the game. Kinda. Some of the AI strategies are based on the behaviour of human players. For example, in the later versions when Ryu dizzies the opponent, he will whiff several jabs. This is…

      ilitiritView on HNParent context

  5. Computer Moves 1 comment

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.