SSE improves long-horizon goal-conditioned RL by using failure and partial-success transitions to identify unreliable subgoals, streamline high-level planning, and outperform prior hierarchical methods on benchmarks.
A note on two problems in connexion with graphs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Combines Contraction Hierarchies with the Connection Scan Algorithm to improve shortest-path queries over bidirectional Dijkstra or A* on Contraction Hierarchies.
citing papers explorer
-
Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning
SSE improves long-horizon goal-conditioned RL by using failure and partial-success transitions to identify unreliable subgoals, streamline high-level planning, and outperform prior hierarchical methods on benchmarks.
-
Combining the Connection Scan Algorithm with Contraction Hierarchies
Combines Contraction Hierarchies with the Connection Scan Algorithm to improve shortest-path queries over bidirectional Dijkstra or A* on Contraction Hierarchies.