Marc G. BellemareKnowledge discovery and lifelong learning, formalizing the aims and qualities of long-lived agents. Design of the simulator and firmware programming. Michael BowlingOffline subjective data analysis, A.R.E. Thomas DegrisLearning representations for reinforcement learning problems in subjective robotics. Anna KoopKnowledge representation in embodied systems, connecting low-level sensori-motor data to abstract concepts. Assistance with the simulator and firmware. Chris RaynerBuilding representations that facilitate learning, research in data prediction, feature selection, and dimensionality reduction. Rich SuttonPrincipal Investigator and inspiration behind the project. Adam WhiteReinforcement learning. Programming for the simulator. |