SLOPE improves MBRL in sparse reward settings by using optimistic distributional regression to build informative potential landscapes that provide better exploration gradients, outperforming baselines across 30+ tasks and real robotic deployments.
Title resolution pending
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
-
SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
SLOPE improves MBRL in sparse reward settings by using optimistic distributional regression to build informative potential landscapes that provide better exploration gradients, outperforming baselines across 30+ tasks and real robotic deployments.