Unicorn: Continual Learning with a Universal, Off-policy Agent
This addresses the problem of continual learning for AI agents in dynamic environments, though it appears incremental as it builds on existing off-policy methods.
The paper tackles the challenge of continual learning in complex 3D domains with sparse rewards by proposing the Unicorn agent architecture, which outperforms baseline agents by jointly representing and learning multiple policies efficiently.
Some real-world domains are best characterized as a single task, but for others this perspective is limiting. Instead, some tasks continually grow in complexity, in tandem with the agent's competence. In continual learning, also referred to as lifelong learning, there are no explicit task boundaries or curricula. As learning agents have become more powerful, continual learning remains one of the frontiers that has resisted quick progress. To test continual learning capabilities we consider a challenging 3D domain with an implicit sequence of tasks and sparse rewards. We propose a novel agent architecture called Unicorn, which demonstrates strong continual learning and outperforms several baseline agents on the proposed domain. The agent achieves this by jointly representing and learning multiple policies efficiently, using a parallel off-policy learning setup.