Evolving Action Abstractions for Real-Time Planning in Extensive-Form Games

Mariño, Julian R. H.; Moraes, Rubens O.; Toledo, Cláudio Fabiano Motta; Lelis, Levi H. S.

doi:10.1609/aaai.v33i01.33012330

Cited by 13 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prior work has investigated various techniques to make Monte Carlo Tree Search (MCTS) applicable to real-time games such as Ms. Pac-Man [Pepels et al, 2014;Ikehata and Ito, 2011], StarCraft [Uriarte and Ontañón, 2016], Wargus [Balla and Fern, 2009], Physical Traveling Salesman Problem [Powley et al, 2012], Quantified Constraint Satisfaction Problem [Baba et al, 2011], and µRTS [Barriga et al, 2018;Mariño et al, 2019]. An example of a recent work in this line is Mariño et al [2019], who study a technique of action abstraction and apply it to MCTS among others to reduce the search space. Barriga et al [2018] study a technique of using non-deterministic rules to reduce the branching in MCTS.…”

Section: Related Workmentioning

confidence: 99%

Real-time tree search with pessimistic scenarios

Osogami,

Takahashi

2019

Preprint

View full text Add to dashboard Cite

Autonomous agents need to make decisions in a sequential manner, under partially observable environment, and in consideration of how other agents behave. In critical situations, such decisions need to be made in real time for example to avoid collisions and recover to safe conditions. We propose a technique of tree search where a deterministic and pessimistic scenario is used after a specified depth. Because there is no branching with the deterministic scenario, the proposed technique allows us to take into account the events that can occur far ahead in the future. The effectiveness of the proposed technique is demonstrated in Pommerman, a multi-agent environment used in a NeurIPS 2018 competition, where the agents that implement the proposed technique have won the first and third places.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-time tree search with pessimistic scenarios

Osogami,

Takahashi

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The problem of using a small set of expert-designed strategies is that the resulting agent can be limited by the expert's knowledge. In Mariño et al (2019), we mitigated this problem by generating a large pool of strategies Z from a small set of strategies designed by experts. We also presented an evolutionary algorithm that returns a subset of Z, which was then used to induce an action abstraction.…”

Section: Introductionmentioning

confidence: 99%

Learning Strategies for Real-Time Strategy Games with Genetic Programming

Mariño

2019

AIIDE

View full text Add to dashboard Cite

Planning in real-time strategy (RTS) games is challenging due to their very large state and action spaces. Action abstractions have shown to be a promising approach for dealing with this challenge. Previous approaches induce action abstractions from a small set of hand-crafted strategies, which are used by algorithms to search only on the actions returned by the strategies. Previous works use a set of expert-designed strategies for inducing action abstractions. The main drawback of this approach is that it limits the agent behaviour to the knowledge encoded in the strategies. In this research, we focus on learning novel and effective strategies for RTS games, to induce action abstractions. In addition to being effective, we are interested in learning strategies that can be easily interpreted by humans, allowing a better understanding of the workings of the resulting agent.

show abstract

“…The generation of action abstractions can be cast as a problem of selecting a subset of pure strategies from a pool of options. It uses Stratified Strategy Selection (SSS) to plan in real time in the space defined by the action abstraction thus generated [68].…”

mentioning

confidence: 99%

A Comparison of Evolutionary and Tree-Based Approaches for Game Feature Validation in Real-Time Strategy Games with a Novel Metric

et al. 2020

View full text Add to dashboard Cite

When it comes to game playing, evolutionary and tree-based approaches are the most popular approximate methods for decision making in the artificial intelligence field of game research. The evolutionary domain therefore draws its inspiration for the design of approximate methods from nature, while the tree-based domain builds an approximate representation of the world in a tree-like structure, and then a search is conducted to find the optimal path inside that tree. In this paper, we propose a novel metric for game feature validation in Real-Time Strategy (RTS) games. Firstly, the identification and grouping of Real-Time Strategy game features is carried out, and, secondly, groups are included into weighted classes with regard to their correlation and importance. A novel metric is based on the groups, weighted classes, and how many times the playtesting agent invalidated the game feature in a given game feature scenario. The metric is used in a series of experiments involving recent state-of-the-art evolutionary and tree-based playtesting agents. The experiments revealed that there was no major difference between evolutionary-based and tree-based playtesting agents.

show abstract

Evolving Action Abstractions for Real-Time Planning in Extensive-Form Games

Cited by 13 publications

References 23 publications

Real-time tree search with pessimistic scenarios

Real-time tree search with pessimistic scenarios

Learning Strategies for Real-Time Strategy Games with Genetic Programming

A Comparison of Evolutionary and Tree-Based Approaches for Game Feature Validation in Real-Time Strategy Games with a Novel Metric

Contact Info

Product

Resources

About