Multi-Objective Reinforcement Learning with Concept Drift
Abstract
Real world environments are non-stationary and include unanticipated changes that contradict what an agent has previously learned. In machine learning, this is called concept drift, a partially-observable change when the environment modifies without notification. Concept drift causes several problems: agents with a decaying exploration fail to adapt, while agents capable of adapting may over xC;t to noise or overwrite previously learned knowledge. Agents in such environments must take steps to mitigate both problems. This problem is compounded because agents typically have multiple tasks to accomplish simultaneously, requiring multi-objective optimization. This work contributes a novel algorithm that combines concept drift learning with multi-objective reinforcement learning to produce an unsupervised technique for learning in non-stationary multiple objective environments. Testing shows that the agent consistently outperforms traditional multi-objective reinforcement learning. It demonstrates that concept drift can be characterized, detected, and recognized using the developed algorithm.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 21, 2017
- Accession Number
- AD1055590
Entities
People
- Frederick C. Webber
Organizations
- Air Force Institute of Technology