Domain-Independent Game Abstraction using Word Embedding Techniques
For game AI researchers, this provides a generalizable abstraction approach that reduces the need for domain-specific analysis, though it is currently less effective than specialized methods.
The paper proposes a domain-independent game abstraction method using word embedding techniques, treating actions as words and gameplay as a corpus. Experiments show the method is effective but does not outperform specialized algorithms tailored to specific games.
Many games of interest in the real world are often intractably large, thereby necessitating the use of game abstraction to shrink them in size, typically by many magnitudes. Over the last two decades, there have been significant advances in game abstraction; however, the domain-specific nature (usually poker) of much of the prior work prevents those techniques from being easily generalized to other settings without extensively analyzing the game at hand. In this paper, we propose a domain-independent approach to game abstraction, which applies word embedding techniques from the field of natural language processing. Treating each action as a word and gameplay data as a corpus, word vectors can be trained to represent each action as a real-valued vector, which can then be clustered to facilitate game abstraction. We also explore the use of foundational embedding models and show that action embeddings obtained this way can capture a surprising amount of information about the underlying game. Experimental results demonstrate that our proposed game abstraction technique is effective, although it does not outperform specialized algorithms tailored to specific games.