Reinforcement Learning as a field has exploded in popularity in recent years, with ambitions to tackle problems in a wide range of real-world applications, such as medicine, robotics and finance. However, there is a gap between the typically small, simulated problems that RL excels at and the larger, more complex, dynamic and unpredictable real-world environments to which we wish to apply RL. To help bridge this gap, a great deal of emphasis has been placed on generalisation, the ability for an RL agent to generalise to new situations.
The focus of this workshop is to expose researchers and students from all across the African continent to the latest advances in the field of generalisation in RL, as well as spark some discussion about the future direction of this nascent field.
The main agenda of the workshop includes keynote talks from top researchers in the field, short talks from a number of African research groups, and a panel discussion on generalisation in RL.