About Me

I'm Joel, and I'm currently a Ph.D. student at the University of Central Florida. My research goal is to write algorithms inspired by natural evolution that continually produce a wild diversity of interesting and complex things.

Publications



2011

Task Switching in Multiagent Learning through Indirect Encoding
David D'Ambrosio, Joel Lehman, Sebastian Risi, and Kenneth O. Stanley
To Appear In: Proceedings of the International Conference on Intelligent Robots and Systems (IROS-2011)

Novelty Search and the Problem with Objectives
Joel Lehman and Kenneth O. Stanley
To Appear In: Genetic Programming Theory and Practice IX (GPTP 2011)

Evolving a Diversity of Virtual Creatures through Novelty Search and Local Competition
Joel Lehman and Kenneth O. Stanley
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2011)

Improving Evolvability through Novelty Search and Self-Adaptation
Joel Lehman and Kenneth O. Stanley
To appear in: Proceedings of the 2011 Congress on Evolutionary Computation

Abandoning Objectives: Evolution Through the Search for Novelty Alone
Joel Lehman and Kenneth O. Stanley
In: Evolutionary Computation journal.

2010

Revising the Evolutionary Computation Abstraction: Minimal Criteria Novelty Search
Joel Lehman and Kenneth O. Stanley
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010).

Efficiently Evolving Programs through the Search for Novelty
Joel Lehman and Kenneth O. Stanley
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010).

Evolving the Placement and Density of Neurons in the HyperNEAT Substrate
Sebastian Risi, Joel Lehman, and Kenneth O. Stanley
In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010).
Winner of the Best Paper Award in the GDS Track at GECCO-2010

Evolving Policy Geometry for Scalable Multiagent Learning
David B. D'Ambrosio, Joel Lehman, Sebastian Risi, and Kenneth O. Stanley
In: Proceedings of the Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2010).

2008

Exploiting Open-Endedness to Solve Problems Through the Search for Novelty
Joel Lehman and Kenneth O. Stanley
In: Proceedings of the Eleventh International Conference on Artificial Life (ALIFE XI).

Software

Novelty Search C++
An implementation of novelty search in C++ that is built on top of Ken Stanley's implementation of the NEAT neuroevolution algorithm in C++.


This page was last updated at Friday January 27, 2012 at 01:51:53 EST.