An agent that plans on a landmark graph built from a locally accurate value function reaches long-range goals faster and more reliably than model-free baselines in sparse-reward environments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mapping State Space using Landmarks for Universal Goal Reaching
An agent that plans on a landmark graph built from a locally accurate value function reaches long-range goals faster and more reliably than model-free baselines in sparse-reward environments.