Safety and Life-long Reinforcement Learning

Agent (red) learning to push orange buttons while avoiding blue danger zones


Random exploration is one of the main mechanisms through which reinforcement learning (RL) solves tasks. However, random exploration can lead to undesirable or catastrophic outcomes when learning in safety-critical environments. In fact, safe learning is one of the major obstacles towards real-world agents that can learn during deployment. This project revolves around approaches that automatically train sub-modules that shape learning such that the agent will instinctively avoid dangers while still being capable of exploring its surroundings to learn new tasks.

Related Research