General video game ai: Competition, challenges and opportunities

D Perez-Liebana, S Samothrakis, J Togelius… - Proceedings of the …, 2016 - ojs.aaai.org
Abstract The General Video Game AI framework and competition pose the problem of
creating artificial intelligence that can play a wide, and in principle unlimited, range of …

A systematic literature review of the successors of “neuroevolution of augmenting topologies”

E Papavasileiou, J Cornelis… - Evolutionary …, 2021 - ieeexplore.ieee.org
NeuroEvolution (NE) refers to a family of methods for optimizing Artificial Neural Networks
(ANNs) using Evolutionary Computation (EC) algorithms. NeuroEvolution of Augmenting …

[PDF][PDF] Deep Learning: A Critical Appraisal

G Marcus - arXiv preprint arXiv:1801.00631, 2018 - indexinvestorportfolios.com
Although deep learning has historical roots going back decades, neither the term" deep
learning" nor the approach was popular just over five years ago, when the field was …

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

D Silver, T Hubert, J Schrittwieser, I Antonoglou, M Lai… - Science, 2018 - science.org
The game of chess is the longest-studied domain in the history of artificial intelligence. The
strongest programs are based on a combination of sophisticated search techniques, domain …

[图书][B] Artificial intelligence and games

GN Yannakakis, J Togelius - 2018 - Springer
Georgios N. Yannakakis Julian Togelius Page 1 Artificial Intelligence and Games Georgios N.
Yannakakis Julian Togelius Page 2 Artificial Intelligence and Games Page 3 Georgios N …

OpenSpiel: A framework for reinforcement learning in games

M Lanctot, E Lockhart, JB Lespiau, V Zambaldi… - arXiv preprint arXiv …, 2019 - arxiv.org
OpenSpiel is a collection of environments and algorithms for research in general
reinforcement learning and search/planning in games. OpenSpiel supports n-player (single …

Human-level control through deep reinforcement learning

V Mnih, K Kavukcuoglu, D Silver, AA Rusu, J Veness… - nature, 2015 - nature.com
The theory of reinforcement learning provides a normative account, deeply rooted in
psychological and neuroscientific perspectives on animal behaviour, of how agents may …

Textworld: A learning environment for text-based games

MA Côté, A Kádár, X Yuan, B Kybartas… - Computer Games: 7th …, 2019 - Springer
We introduce TextWorld, a sandbox learning environment for the training and evaluation of
RL agents on text-based games. TextWorld is a Python library that handles interactive play …

Thinking fast and slow with deep learning and tree search

T Anthony, Z Tian, D Barber - Advances in neural …, 2017 - proceedings.neurips.cc
Sequential decision making problems, such as structured prediction, robotic control, and
game playing, require a combination of planning policies and generalisation of those plans …

The arcade learning environment: An evaluation platform for general agents

MG Bellemare, Y Naddaf, J Veness… - Journal of Artificial …, 2013 - jair.org
In this article we introduce the Arcade Learning Environment (ALE): both a challenge
problem and a platform and methodology for evaluating the development of general, domain …