Genetic Algorithms for Evolution of QWOP Gaits
QWOP is a browser-based, 2-dimensional flash game in which the player controls an Olympic sprinter competing in a simulated 100-meter race. The goal of the game is to advance the runner to the end of the 100-meter race as quickly as possible using the Q, W, O, and P keys, which control the muscles in the sprinters legs. Despite the game simple controls and straightforward goal, it is renowned for its difficulty and unintuitive gameplay. In this paper, we attempt to automatically discover effective QWOP gaits. We describe a programmatic interface developed to play the game, and we introduce several variants of a genetic algorithm tailored to solve this problem. We present experimental results on the effectiveness of various representations, initialization strategies, evolution paradigms, and parameter control mechanisms.
Code (1)
Similar Papers 제목 키워드 기반
Robustness for Free: Quality-Diversity Driven Discovery of Agile Soft Robotic Gaits
Soft robotics aims to develop robots able to adapt their behavior across a wide range of unstructured and unknown environments. A critical challenge of soft robotic control is that nonlinear dynamics often result in comp…
DiversityMorphological Development at the Evolutionary Timescale: Robotic Developmental Evolution
Evolution and development operate at different timescales; generations for the one, a lifetime for the other. These two processes, the basis of much of life on earth, interact in many non-trivial ways, but their temporal…
Developmental LearningEvolutionary algorithms
This manuscript contains an outline of lectures course "Evolutionary Algorithms" read by the author. The course covers Canonic Genetic Algorithm and various other genetic algorithms as well as evolutionary strategies, ge…
Evolutionary AlgorithmsEpigenetic opportunities for Evolutionary Computation
Evolutionary Computation is a group of biologically inspired algorithms used to solve complex optimisation problems. It can be split into Evolutionary Algorithms, which take inspiration from genetic inheritance, and Swar…
Evolutionary AlgorithmsSurvey of Genetic and Differential Evolutionary Algorithm Approaches to Search Documents Based On Semantic Similarity
Identifying similar documents within extensive volumes of data poses a significant challenge. To tackle this issue, researchers have developed a variety of effective distributed computing techniques. With the advancement…
Semantic Similarity