HRC learns the causal structure among subgoals and prioritizes interventions on the subgoals that matter most for the final goal, lowering training cost in hierarchical RL.
For” loop, it records a trajectory τj. The “While
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Reinforcement Learning with Targeted Causal Interventions
HRC learns the causal structure among subgoals and prioritizes interventions on the subgoals that matter most for the final goal, lowering training cost in hierarchical RL.