AXIOM, a gradient-free active inference agent with growing and pruning object-centric mixture models, achieves better or similar reward than BBF and DreamerV3 after 10,000 interactions on the custom Gameworld 10k suite.
Pure reasoning in 12-month-old infants as probabilistic inference,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
AXIOM, a gradient-free active inference agent with growing and pruning object-centric mixture models, achieves better or similar reward than BBF and DreamerV3 after 10,000 interactions on the custom Gameworld 10k suite.