Dual Advantage Fields converts bilinear dual value models into local advantage scores via learned action-effect models, equaling the goal-conditioned Bellman advantage under realizability and improving aggregate metrics on OGBench locomotion, manipulation, and puzzle tasks.
Offline goal-conditioned reinforcement learning with quasimetric representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
A zero-shot STL planner combines a map-conditioned Transformer with a disjunctive heuristic and Transitive RL to achieve better generalization across dynamic semantic maps.
TRM trains a small horizon-matched pairwise head on trajectory data to improve terminal-state ranking in latent MPC, raising success from 7% to 97% on TwoRoom and 32.7% to 84% on PLDM without changing the encoder or dynamics.
citing papers explorer
-
Dual Advantage Fields
Dual Advantage Fields converts bilinear dual value models into local advantage scores via learned action-effect models, equaling the goal-conditioned Bellman advantage under realizability and improving aggregate metrics on OGBench locomotion, manipulation, and puzzle tasks.
-
Zero-Shot Signal Temporal Logic Planning with Disjunctive Branch Selection in Dynamic Semantic Maps
A zero-shot STL planner combines a map-conditioned Transformer with a disjunctive heuristic and Transitive RL to achieve better generalization across dynamic semantic maps.
-
Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics
TRM trains a small horizon-matched pairwise head on trajectory data to improve terminal-state ranking in latent MPC, raising success from 7% to 97% on TwoRoom and 32.7% to 84% on PLDM without changing the encoder or dynamics.