Splendor is modern board game well known in the board games community (ranked 19th on boardgamegeek in the family games genre).
It has simple discrete mechanics simple to grasp for the players. However, they can be intertwined together to create a complex gameplay that is often hard to predict for humans.
How can AIs play this game? Can we expect a strong gameplay as Alpha-Go in Go? Do we humans have good chances of beating it?
I guess the only way to know that is, you guessed it, play!
The demo will consist in a simplified and shortened version of Splendor:
- 2 players: 1 human vs 1 AI
- limited decks
- limited turns
- reduced end-game prestige point target
The players will be presented with a simplified interface of the game on the screen and they will pick actions in turn against the AI trying to see who will win this one! Let's play!
Fugl: A Meditative Bird Flying Experience
I am part of Team Fugl, which has been building a meditative flying game for the last 3.5 years. Fugl is a sandbox game where you create the story, playing as a shape-shifting bird. Relax and feel the breeze under your wings as you glide serenely across picturesque landscapes, or kick up the excitement and soar up steep cliffs like an eagle. With no set rules the free roaming gameplay lets you discover the beauty and secrets of the world at your own pace and dares you to make your own meaning for a stress-free experience.
The demo will be running on an Oculus Rift (S) with Oculus Touches. The experience is currently available on the Oculus store, and is by far the most interesting version of the game, as you become embedded in the body of giant voxelized bird.
The demo is nearly always well-received when shown publicly. With its colourful but non-violent experience, it attracts a wide audience, and we see it as an experience that is part of a movement redefining what video games can be. In fact, though it is not the direct purpose of the game, it is not uncommon for people to tell us, how it helps them anxiety or depression.
Technically, the game might also be of interest to the attendees, as all of the games’ biomes are procedurally generated.
This is a link to the experience: https://www.oculus.com/experiences/rift/1549570518416178
Time to Die: Death Prediction in Dota 2 using Deep Learning
Ryan Spick,Charlie Ringer, Peter York, Adam Katona
Esports have become major international competitions with hundreds of millions of spectators. Esports games generate massive amounts of telemetry data.
Using these to predict the outcome of esports matches has received considerable attention, but micro-predictions, which seek to predict events inside a match, is as yet unknown territory. Micro-predictions are, however, of perennial interest across esports commentators and audience, because they provide the ability to observe events that might otherwise be missed. Esports games are highly complex with fast-moving action where the balance of a game can change in the span of seconds, and where events can happen in multiple areas of the playing field at the same time. Such events can happen rapidly, and it is easy for commentators and viewers alike to miss an event and only observe the impact of this event. In Dota 2, a player’s hero being killed by the opposing team is a key event of interest to commentators and audience.
We present a deep learning network which provides accurate death predictions within a five-second window. In this demo we will showcase the model’s predictions alongside replays of Dota 2 games. The replays are interactive, users can change replay speed, jump to interesting events, and analyze the performance of the predictions.