I am a PhD student at the Autonomous Agents and Distributed Intelligence Lab, part of the Collaborative Robotics and Intelligent Systems (CoRIS) Institute at Oregon State University, where I work on learning and coordination in multi-robot systems. I am advised by Dr. Kagan Tumer.

My research is at the intersection of reinforcement learning, evolutionary robotics and game theory. I am interested in developing methods that enable asymmetric robots (robots with diverse capabilities and objectives) to cooperate and work together as teams with a variety of partners. Discovering the relationships between robots and their influence on the team dynamics is crucial for learning adaptable behaviors that can generalize across a variety of tasks and team compositions. For cultivating such relationships, my work investigates Quality-Diversity and Coevolutionary reinforcement learning algorithms which encourage novel behaviors and teamwork as a key component of the learning process.



selected publications


  • Learning Synergies for Multi-Objective Optimization in Asymmetric Multiagent Systems
    In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). 2023.
    G. Dixit, K. Tumer [ pdf ]
  • Learning Inter-Agent Synergies in Asymmetric Multiagent Systems
    Proceedings of the 22nd International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2023.
    G. Dixit, K. Tumer [ pdf ]
  • Diversifying behaviors for learning in Asymmetric Multiagent Systems
    In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO). 2022.
    G. Dixit, E. Gonzalez, K. Tumer [ pdf ]
  • Balancing Teams with Quality-Diversity for Heterogeneous Multiagent Coordination
    In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2022.
    G. Dixit, K. Tumer [ pdf ]
  • Gaussian Processes as Multiagent Reward Models
    Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2020.
    G. Dixit, S. Airiau, K. Tumer [ pdf ]
  • Dirichlet-Multinomial Counterfactual Rewards for Heterogeneous Multiagent Systems
    In 2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), IEEE. 2019.
    G. Dixit, N. Zerbel, K. Tumer [ pdf ]