Unsupervised training sequence design: Efficient and generalizable agent training
To train generalizable Reinforcement Learning (RL) agents, researchers recently proposed the Unsupervised Environment Design (UED) framework, in which a teacher agent creates a very large number of training environments and a student agent trains on the experiences in these environments to be robust...
Saved in:
Main Authors: | LI, Wenjun, VARAKANTHAM, Pradeep |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9362 https://ink.library.smu.edu.sg/context/sis_research/article/10362/viewcontent/29268_Article_Text_33322_1_2_20240324_pvoa.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Offline RL with discrete proxy representations for generalizability in POMDPs
by: GU, Pengjie, et al.
Published: (2023) -
Knowledge generation for zero-shot knowledge-based VQA
by: CAO, Rui, et al.
Published: (2024) -
A Surprise Triggered Adaptive and Reactive (STAR) Framework for Online Adaptation in Non-stationary Environments
by: NGUYEN, Truong-Huy Dinh, et al.
Published: (2009) -
Approximate Inference in Collective Graphical Models
by: SHELDON, Daniel, et al.
Published: (2013) -
Influence Diagrams With Memory States: Representation and Algorithms
by: WU, Xiaojian, et al.
Published: (2011)