A proposed transfer algorithm, GGPI, applies successor features to alternating zero-sum Markov games, but its central theorem is not proven as written.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Successor Features for Transfer in Alternating Markov Games
A proposed transfer algorithm, GGPI, applies successor features to alternating zero-sum Markov games, but its central theorem is not proven as written.