11 papers
Temporal-Difference Learning for Dragonchess
Jim O'Connor, Annika Hoag, Sarah Goyette +1
Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The game chall…
Decentralized Evolution of Hexapod Gaits with Independent Leg Controllers
Gary B. Parker, John Asaro, Jim O'Connor
This paper presents a novel approach to hexapod locomotion by evolving each leg's gait independently through a decentralized evolutionary algorithm. Using the Webots simulator and…
Niching Agents in The Core
Gary B. Parker, Jim O'Connor, John Asaro
The Core is a unique competitive co-evolution algorithm that allows agents to evolve autonomous control without utilizing a traditional fitness function. The agents evolve via loca…
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…
Learning Dark Souls Combat Through Pixel Input With Neuroevolution
Jim O'Connor, Gary B. Parker, Mustafa Bugti
This paper investigates the application of Neuroevolution of Augmenting Topologies (NEAT) to automate gameplay in Dark Souls, a notoriously challenging action role-playing game cha…
NeuroPAL: Punctuated Anytime Learning with Neuroevolution for Macromanagement in Starcraft: Brood War
Jim O'Connor, Yeonghun Lee, Gary B Parker
StarCraft: Brood War remains a challenging benchmark for artificial intelligence research, particularly in the domain of macromanagement, where long-term strategic planning is requ…