Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new useriNNk: A Multi-Player Game to Deceive a Neural Network
96
0
0.0
(
0
)
Added by
Jichen Zhu
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper presents iNNK, a multiplayer drawing game where human players team up against an NN. The players need to successfully communicate a secret code word to each other through drawings, without being deciphered by the NN. With this game, we aim to foster a playful environment where players can, in a small way, go from passive consumers of NN applications to creative thinkers and critical challengers.
rate research
Read More
Applying neural network (NN) methods in games can lead to various new and exciting game dynamics not previously possible. However, they also lead to new challenges such as the lack of large, clean datasets, varying player skill levels, and changing gameplay strategies. In this paper, we focus on the adversarial player strategy aspect in the game iNNk, in which players try to communicate secret code words through drawings with the goal of not being deciphered by a NN. Some strategies exploit weaknesses in the NN that consistently trick it into making incorrect classifications, leading to unbalanced gameplay. We present a method that combines transfer learning and ensemble methods to obtain a data-efficient adaptation to these strategies. This combination significantly outperforms the baseline NN across all adversarial player strategies despite only being trained on a limited set of adversarial examples. We expect the methods developed in this paper to be useful for the rapidly growing field of NN-based games, which will require new approaches to deal with unforeseen player creativity.
The advent of artificial intelligence (AI) and machine learning (ML) bring human-AI interaction to the forefront of HCI research. This paper argues that games are an ideal domain for studying and experimenting with how humans interact with AI. Through a systematic survey of neural network games (n = 38), we identified the dominant interaction metaphors and AI interaction patterns in these games. In addition, we applied existing human-AI interaction guidelines to further shed light on player-AI interaction in the context of AI-infused systems. Our core finding is that AI as play can expand current notions of human-AI interaction, which are predominantly productivity-based. In particular, our work suggests that game and UX designers should consider flow to structure the learning curve of human-AI interaction, incorporate discovery-based learning to play around with the AI and observe the consequences, and offer users an invitation to play to explore new forms of human-AI interaction.
EcoTRADE is a multi player network game of a virtual biodiversity credit market. Each player controls the land use of a certain amount of parcels on a virtual landscape. The biodiversity credits of a particular parcel depend on neighboring parcels, which may be owned by other players. The game can be used to study the strategies of players in experiments or classroom games and also as a communication tool for stakeholders participating in credit markets that include spatially interdependent credits.
SimDialog is a visual editor for dialog in computer games. This paper presents the design of SimDialog, illustrating how script writers and non-programmers can easily create dialog for video games with complex branching structures and dynamic response characteristics. The system creates dialog as a directed graph. This allows for play using the dialog with a state-based cause and effect system that controls selection of non-player character responses and can provide a basic scoring mechanism for games.
We introduce a new virtual environment for simulating a card game known as Big 2. This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many current reinforcement learning methods. We then use the recently proposed Proximal Policy Optimization algorithm to train a deep neural network to play the game, purely learning via self-play, and find that it is able to reach a level which outperforms amateur human players after only a relatively short amount of training time and without needing to search a tree of future game states.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
