MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
원문 초록
Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly learn such a meta-policy. In this paper, we propose a new meta-RL algorithm called Meta Goal-generation for Hierarchical RL (MGHRL). Instead of directly generating policies over primitive action space for new tasks, MGHRL learns to generate high-level meta strategies over subgoals given past experience and leaves the rest of how to achieve subgoals as independent RL subtasks. Our empirical results on several challenging simulated robotics environments show that our method enables more efficient and generalized meta-learning from past experience.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Hierarchical Reinforcement Learning and Value Optimization for Challenging Quadruped Locomotion
HiLight: A Hierarchical Reinforcement Learning Framework with Global Adversarial Guidance for Large-Scale Traffic Signal Control
Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation
Meta Reinforcement Learning for Multi-Task Offloading in Vehicular Edge Computing
Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition
High-Throughput Distributed Reinforcement Learning via Adaptive Policy Synchronization
토론
이 논문과 연결된 포럼 글이 아직 없습니다.