Collaborating Authors

Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scales Machine Learning

We introduce gym-city, a Reinforcement Learning environment that uses SimCity 1's game engine to simulate an urban environment, wherein agents might seek to optimize one or a combination of any number of city-wide metrics, on gameboards of various sizes. We focus on population, and analyze our agents' ability to generalize to larger map-sizes than those seen during training. The environment is interactive, allowing a human player to build alongside agents during training and inference, potentially influencing the course of their learning, or manually probing and evaluating their performance. To test our agents' ability to capture distance-agnostic relationships between elements of the gameboard, we design a minigame within the environment which is, by design, unsolvable at large enough scales given strictly local strategies. Given the game engine's extensive use of Cellular Automata, we also train our agents to "play" Conway's Game of Life -- again optimizing for population -- and examine their behaviour at multiple scales. To make our models compatible with variable-scale gameplay, we use Neural Networks with recursive weights and structure -- fractals to be truncated at different depths, dependent upon the size of the gameboard.

BTT-Go: An Agent for Go that Uses a Transposition Table to Reduce the Simulations and the Supervision in the Monte-Carlo Tree Search

AAAI Conferences

This paper presents BTT-Go: an agent for Go whose ar- chitecture is based on the well-known agent Fuego, that is, its search process for the best move is based on sim- ulations of games performed by means of Monte- Carlo Tree Search (MCTS). In Fuego, these simulations are guided by supervised heuristics called prior knowledge and play-out policy. In this context, the goal behind the BTT-Go proposal is to reduce the supervised character of Fuego, granting it more autonomy. To cope with this task, the BTT-Go counts on a Transposition Table (TT) whose role is not to waste the history of the nodes that have already been explored throughout the game. By this way, the agent proposed here reduces the super- vised character of Fuego by replacing, whenever pos- sible, the prior knowledge and the play-out policy with the information retrieved from the TT. Several evalua- tive tournaments involving BTT-Go and Fuego confirm that the former obtains satisfactory results in its purpose of attenuating the supervision in Fuego without losing its competitiveness, even in 19x19 game-boards.

General Board Game Playing for Education and Research in Generic AI Game Learning Artificial Intelligence

We present a new general board game (GBG) playing and learning framework. GBG defines the common interfaces for board games, game states and their AI agents. It allows one to run competitions of different agents on different games. It standardizes those parts of board game playing and learning that otherwise would be tedious and repetitive parts in coding. GBG is suitable for arbitrary 1-, 2-, ..., N-player board games. It makes a generic TD($\lambda$)-n-tuple agent for the first time available to arbitrary games. On various games, TD($\lambda$)-n-tuple is found to be superior to other generic agents like MCTS. GBG aims at the educational perspective, where it helps students to start faster in the area of game learning. GBG aims as well at the research perspective by collecting a growing set of games and AI agents to assess their strengths and generalization capabilities in meaningful competitions. Initial successful educational and research results are reported.

Here's Everything Facebook Announced at F8, From VR to Bots


Facebook's new augmented reality tools will let you place virtual objects into the real world when you view your surroundings through your phone. Leave messages on the fridge for your spouse, or tag businesses with floating notes and tips written on walls. We'll get AR games that incorporate real-world objects thanks to a technology called "SLAM" (simultaneous location and mapping) that lays a 3-D grid over the table in front of you, turning it into a gameboard. Also, we'll get AR art, pieces only viewable through your phone. As Zuckerberg said, "This is going to be a thing in the future--people standing around looking at blank walls."


International Business Times

A sneak peek at "Pretty Little Liars" Season 7, episode 18, reveals that despite their choice to start a future together, Emily (Shay Mitchell) and Alison's (Sasha Pieterse) plans will be interrupted by A.D. Seeing the unhappy look on her face, Emily turns around and quickly begins to share Alison's sentiments. Did A.D. force Aria to relocate Liar's Lament to Alison's room or is she playing a new game? "Pretty Little Liars" Season 7, episode 18 Emily (Shay Mitchell) and Alison's (Sasha Pieterse) special moment is ruined by A.D.'s latest scheme.