8 papers
DSLE: A Learning Environment for Dark Souls Boss Encounters
Derin Gezgin, Jim O'Connor, Tanner Goodwin +1
We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game-playing agent benchmarks th…
Evolutionary Transfer Learning for Dragonchess
Jim O'Connor, Annika Hoag, Sarah Goyette +1
Dragonchess, a three-dimensional chess variant introduced by Gary Gygax, presents unique strategic and computational challenges that make it an ideal environment for studying the t…
Playing Atari Space Invaders with Sparse Cosine Optimized Policy Evolution
Jim O'Connor, Jay B. Nash, Derin Gezgin +1
Evolutionary approaches have previously been shown to be effective learning methods for a diverse set of domains. However, the domain of game-playing poses a particular challenge f…
Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong
Jim O'Connor, Derin Gezgin, Gary B. Parker
We present Evo-Sparrow, a deep learning-based agent for AI decision-making in Sparrow Mahjong, trained by optimizing Long Short-Term Memory (LSTM) networks using Covariance Matrix…
Evolving Neural Controllers for Xpilot-AI Racing Using Neuroevolution of Augmenting Topologies
Jim O'Connor, Nicholas Lorentzen, Gary B. Parker +1
This paper investigates the development of high-performance racing controllers for a newly implemented racing mode within the Xpilot-AI platform, utilizing the Neuro Evolution of A…
SCOPE for Hexapod Gait Generation
Jim O'Connor, Jay B. Nash, Derin Gezgin +1
Evolutionary methods have previously been shown to be an effective learning method for walking gaits on hexapod robots. However, the ability of these algorithms to evolve an effect…