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.
Goal-conditioned reinforcement learning with disentanglement-based reachability planning.arXiv preprint arXiv:2307.10846, 2023
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
-
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.