GCRL and MISL are unified as control maximization, with three inequivalent GCRL formulations each matched to a MISL objective via bounds on goal-sensitivity.
(126) Equality holds ifJ(s, g, π {g′,.}) = 0for allg ′ ̸=gandp goal = Unif(S)
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
-
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
GCRL and MISL are unified as control maximization, with three inequivalent GCRL formulations each matched to a MISL objective via bounds on goal-sensitivity.