Exploring a Learning Architecture for General Game Playing

Gunawan, Alvaro; Ruan, Ji; Thielscher, Michael; Narayanan, Ajit

doi:10.1007/978-3-030-64984-5_23

Cited by 4 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GAZ [7] is the first deep reinforcement learning algorithm in GGP to outperform the UCT benchmark in most games except Babel [9,19]. The main process of the algorithm is almost the same as in Alp-haZero, as shown in Figure 1.…”

Section: Gazmentioning

confidence: 98%

“…Deep reinforcement learning (DRL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. It has had many successful applications in games [3,6,14,15,16,17,18] and has been recently introduced into GGP [7,9,19,20].…”

Section: Drl For Ggpmentioning

confidence: 99%

“…We will describe GAZ in details later. The same year, GGPZero [9], which features a structure similar to GAZ but a different game reasoner, was released. This work analyzed various factors affecting agent performance, but its performance was inferior to GAZ.…”

Section: Drl For Ggpmentioning

confidence: 99%

“…It removes the limitation on game type and can automatically design the neural networks according to the number of game propositions [8]. It is the first deep reinforcement learning algorithm that outperforms the UCT benchmark in all games [7,9,10], except in multiplayer cooperative games like Babel. However, unlike Al-phaZero, GAZ employs fully connected networks instead of convolutional neural networks (CNNs).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Convolutional Neural Network Approach to General Game Playing

Wang,

Zhang,

Jiang

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

General Game Playing (GGP), a research field aimed at developing agents that master different games in a unified way, is regarded as a necessary step towards creating artificial general intelligence. With the success of deep reinforcement learning (DRL) in games like Go, chess, and shogi, it has been recently introduced to GGP and is regarded as a promising technique to achieve the goal of GGP. However, the current work uses fully connected neural networks and is thus unable to efficiently exploit the topological structure of game states. In this paper, we propose an approach to applying general-purposed convolutional neural networks to GGP and implement a DRL-based GGP player. Experiments indicate that the built player not only outperforms the previous algorithm and UCT benchmark in a variety of games but also requires less training time.

show abstract

Section: Gazmentioning

confidence: 98%

Section: Drl For Ggpmentioning

confidence: 99%

Section: Drl For Ggpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Convolutional Neural Network Approach to General Game Playing

Wang,

Zhang,

Jiang

2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…Although the architecture presented in AlphaZero was general across the three games, the networks had were specific for each game and had to be trained separately due to the varying state representations. Several recent work (Goldwaser and Thielscher 2020;Gunawan et al 2020) have extended the methods in Alp-haZero to the domain of GGP and shown their effectiveness. The neural networks are used similarly as in AlphaZero for optimal move selection and are specific for individual games too.…”

Section: Related Workmentioning

confidence: 99%

A Graph Neural Network Reasoner for Game Description Language

Gunawan

Ruan

Huang

2022

Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning

Self Cite

View full text Add to dashboard Cite

General Game Playing (GGP) aims to develop agents that are able to play any game with only rules given. The game rules are encoded in the Game Description Language (GDL). A GGP player processes the game rules to obtain game states and expand the game tree search for an optimal move. The recent accomplishments of AlphaGo and AlphaZero have triggered new works in extending neural network approaches to GGP. In these works, the neural networks are used only for optimal move selection, while the components dealing with GDL still use logic-based methods. This motivates us to explore if a neural network based method would be able to approximate the logical inference in GDL with a high accuracy. The structured nature of logic tends to be a difficulty for neural networks, which rely heavily on statistical features. Inspired by the recent works on neural network learning for logical entailments, we propose a neural network based reasoner that is able to learn logical inferences for GDL. We present three key contributions: (i) a general, game-agnostic graph-based representation for game states described in GDL, (ii) methods for generating samples and datasets to frame the GDL inference task as a neural network based machine learning problem and (iii) a GNN based neural reasoner that is able to learn and infer various game states with a high accuracy and has some capability of transfer learning across games.

show abstract