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

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning — mentioned by minimaxir

Wed, 18 Jul 2018 17:21:04 GMT

> 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 is interesting. The Super Smash Bros. Melee AI paper noted that they had to keep the reaction times to superhuman levels in order for the model to converge (albeit DOTA is a bit different from Melee): https://arxiv.org/abs/1702.06230

Paper and discussion history. A mention is not an endorsement.

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning — mentioned by chis

Thu, 14 Dec 2017 05:00:41 GMT

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 the day these papers are from master's students. I think they're both impressive in that context. https://arxiv.org/pdf/1702.06230.pdf

Paper and discussion history. A mention is not an endorsement.

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning — mentioned by canjobear

Wed, 11 Oct 2017 21:26:44 GMT

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

Paper and discussion history. A mention is not an endorsement.

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning — mentioned by ilitirit

Tue, 18 Apr 2017 13:10:50 GMT

> 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 widely regarded as a tribute to a combovideo maker known as TZW[1] who often did this in his videos. With regards to actual Fighting Game strategy, the AI in Super Street Fighter II absolutely uses tactics employed by real players. These are a few off the top of my head: - Tick throws - Whiff aerial attacks into command…

Paper and discussion history. A mention is not an endorsement.

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning — mentioned by chumali

Wed, 05 Apr 2017 10:43:47 GMT

Didn't this already happen? https://arxiv.org/abs/1702.06230

Paper and discussion history. A mention is not an endorsement.

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

Wed, 22 Feb 2017 23:27:17 GMT

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

202 points; 55 discussion replies on HN. Paper and source history. A submission is not an endorsement.