Model-based meta reinforcement learning using graph structured surrogate models and amortized policy search
Q Wang, H Van Hoof - International Conference on Machine …, 2022 - proceedings.mlr.press
Reinforcement learning is a promising paradigm for solving sequential decision-making
problems, but low data efficiency and weak generalization across tasks are bottlenecks in …
problems, but low data efficiency and weak generalization across tasks are bottlenecks in …
Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models
Q Wang, H van Hoof - arXiv preprint arXiv:2102.08291, 2021 - arxiv.org
Reinforcement learning is a promising paradigm for solving sequential decision-making
problems, but low data efficiency and weak generalization across tasks are bottlenecks in …
problems, but low data efficiency and weak generalization across tasks are bottlenecks in …