Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.
Can we really learn one representation to optimize all rewards?arXiv preprint arXiv:2602.11399, 2026
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
-
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.