Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning
원문 초록
In dynamic domains such as autonomous robotics and video game simulations, agents must continuously adapt to new tasks while retaining previously acquired skills. This ongoing process, known as Continual Reinforcement Learning, presents significant challenges, including the risk of forgetting past knowledge and the need for scalable solutions as the number of tasks increases. To address these issues, we introduce HIerarchical LOW-rank Subspaces of Policies (HILOW), a novel framework designed for continual learning in offline navigation settings. HILOW leverages hierarchical policy subspaces to enable flexible and efficient adaptation to new tasks while preserving existing knowledge. We demonstrate, through a careful experimental study, the effectiveness of our method in both classical MuJoCo maze environments and complex video game-like simulations, showcasing competitive performance and satisfying adaptability according to classical continual learning metrics, in particular regarding memory usage. Our work provides a promising framework for real-world applications where continuous learning from pre-collected data is essential.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Deep Reinforcement Learning with Gradient Eligibility Traces
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback
Continual Reinforcement Learning by Planning with Online World Models
A Survey of Continual Reinforcement Learning
Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review
토론
이 논문과 연결된 포럼 글이 아직 없습니다.