I Know How: Combining Prior Policies to Solve New Tasks
This work addresses the problem of efficient adaptation to new tasks in reinforcement learning for agents, though it appears incremental as it builds on existing methodologies by providing a common formalization.
The paper tackles the challenge of catastrophic forgetting and computational inefficiency in multi-task reinforcement learning by proposing the I Know How (IKH) framework, which emphasizes modularity and compositionality of prior knowledge to enhance learning and adaptation in dynamic environments, and demonstrates its performance in a simulated driving environment compared to state-of-the-art approaches.
Multi-Task Reinforcement Learning aims at developing agents that are able to continually evolve and adapt to new scenarios. However, this goal is challenging to achieve due to the phenomenon of catastrophic forgetting and the high demand of computational resources. Learning from scratch for each new task is not a viable or sustainable option, and thus agents should be able to collect and exploit prior knowledge while facing new problems. While several methodologies have attempted to address the problem from different perspectives, they lack a common structure. In this work, we propose a new framework, I Know How (IKH), which provides a common formalization. Our methodology focuses on modularity and compositionality of knowledge in order to achieve and enhance agent's ability to learn and adapt efficiently to dynamic environments. To support our framework definition, we present a simple application of it in a simulated driving environment and compare its performance with that of state-of-the-art approaches.