AgentOWL jointly learns an abstract world model and hierarchical neural options to acquire more skills with less data and better generalization than baselines on Object-Centric Atari games.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Joint Learning of Hierarchical Neural Options and Abstract World Model
AgentOWL jointly learns an abstract world model and hierarchical neural options to acquire more skills with less data and better generalization than baselines on Object-Centric Atari games.