Viewing profile — jakobnicolaus
jakobnicolaus
HN member- Joined
- Wed, Nov 15, 2017, 9:07 AM UTC
- HN karma
- 12
- Public activity
- 13 items
- HN profile
- View on Hacker News ↗
About jakobnicolaus
No profile information was provided.
Recent public activity
-
comment
Comment #21732057
We are entirely focused on the self-play setting in which the goal is to learn the highest performing policy for a team of agents all trained together. The Hanabi Challenge also ou…
-
comment
Comment #21732031
We haven't yet analyzed the gameplay to look for examples of these well-known human Hanabi conventions. All the code and agents are open-sourced though, so feel free to take a look…
-
comment
Comment #21732019
There are unique challenges around learning effective communication protocols that appear in cooperative settings, which was the focus of this work. Getting robust superhuman perfo…
-
comment
Comment #19149843
Absolutely, please shoot me an email. Did I mention that we link out random games our bot played in the BAD paper? Sorry for the late reply!
-
comment
Comment #19092261
Sure, but in Hanabi the point is to be as informative as possible, while in poker it should be the opposite (unless you collude).
-
comment
Comment #19091115
Hanabi is fully cooperative and entirely focused on communication. I think it's good to have a testbed that isolates these challenges, rather confounding them with the zero-sum (co…
-
comment
Comment #19091105
The good news is that we have open-sourced the environment, so if you think it's easy I would love to see a simple method that solves it.
-
comment
Comment #19089619
yes - this was the focus of our method: Allowing agents to interpret the actions of others, while also learning to be interpretable when observed by other agents.
-
comment
Comment #19089253
Yes, but actively communicating with some of the other players through agreed conventions would probably count as collusion and be illegal in N-player poker..
-
comment
Comment #19089243
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 a…
-
comment
Comment #19089203
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…
-
comment
Comment #19089178
Hanabi is a multi-agent problem. Unfortunately gym doesn't natively support multi-agent action and state spaces.
-
comment
Comment #15702456
A couple of years ago I built an app (PayMeMaybe) which uses this idea to settle small debts between friends: https://play.google.com/store/apps/details?id=app.paymemaybe... Wasn't…