REPTILE: A Proactive Real-Time Deep Reinforcement Learning Self-adaptive Framework
This work addresses the challenge of building self-adaptive software systems for dynamic environments, but it appears incremental as it builds on existing Deep Reinforcement Learning methods without claiming major breakthroughs.
The authors tackled the problem of developing software systems that can proactively adapt to environmental and architectural changes by proposing REPTILE, a framework using Deep Reinforcement Learning to predict and react to novelties in real-time, resulting in a system that extracts time-changing models and evolves its agent architecture based on possible actions.
In this work a general framework is proposed to support the development of software systems that are able to adapt their behaviour according to the operating environment changes. The proposed approach, named REPTILE, works in a complete proactive manner and relies on Deep Reinforcement Learning-based agents to react to events, referred as novelties, that can affect the expected behaviour of the system. In our framework, two types of novelties are taken into account: those related to the context/environment and those related to the physical architecture itself. The framework, predicting those novelties before their occurrence, extracts time-changing models of the environment and uses a suitable Markov Decision Process to deal with the real-time setting. Moreover, the architecture of our RL agent evolves based on the possible actions that can be taken.