Exploring Meta-learned Curiosity Algorithms
Keywords: reinforcement-learning, curiosity, exploration, meta-learning
Blogpost Url: https://iclr-blogposts.github.io/2024/blog/exploring-meta-learned-curiosity-algorithms/
Abstract: This blog post delves into Alet et al.'s ICLR 2020 paper, Meta-learning curiosity algorithms, which introduces a unique approach to meta-learning curiosity algorithms. Instead of meta-learning neural network weights, the focus is on meta-learning pieces of code, allowing it to be interpretable by humans. The post explores the two meta-learned algorithms, namely Fast Action Space Transition (FAST) and Cycle-Consistency Intrinsic Motivation (CCIM).
Ref Papers: https://arxiv.org/abs/2003.05325
Id Of The Authors Of The Papers: ~Ferran_Alet1,~Martin_F_Schneider1,~Tomás_Lozano-Pérez1,~Leslie_Pack_Kaelbling1
Conflict Of Interest: There's no conflict of interest.
Submission Number: 16
Loading