OPSRs enable limited optimal transfer via predictive state abstractions, extended by reusable OPSR-based skills to speed up RL learning in new tasks without pre-processing.
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
-
Predictive Representations for Skill Transfer in Reinforcement Learning
OPSRs enable limited optimal transfer via predictive state abstractions, extended by reusable OPSR-based skills to speed up RL learning in new tasks without pre-processing.