RLA trains a high-level subgoal generator using the triangle inequality in value space, and the paper claims proofs of optimality and bounded suboptimality under idealized and bounded-error conditions.
Near-optimal regret bounds for stochastic shortest path
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.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks
RLA trains a high-level subgoal generator using the triangle inequality in value space, and the paper claims proofs of optimality and bounded suboptimality under idealized and bounded-error conditions.