Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning · HackerPapers discussions

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning — mentioned by jakobnicolaus

Tue, 05 Feb 2019 20:07:59 GMT

Thanks for your summary of Hanabi! You can find an example of your hypothetical AI in our recent paper: https://arxiv.org/abs/1811.01458. Note that all the conventions and rules are learned though, rather than hand coded. And your 'giant lookup table', is just a feedforward neural network. We also link out 300 games in case you are curious to see how it works.

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

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning — mentioned by jakobnicolaus

Tue, 05 Feb 2019 20:03:18 GMT

I think neural networks will be part of the solution, but they are probably not the entire answer. For an example of a method that combines Deep RL with Bayesian reasoning, you can take a look at our recent paper (https://arxiv.org/abs/1811.01458). BAD achieves best known scores in for 2 player Hanabi in self-play.

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