GBER combines back-stepping experience replay with HER-style relabeling and rfaab sampling, improving learning speed and stability in sparse-reward mazes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalized Back-Stepping Experience Replay in Sparse-Reward Environments
GBER combines back-stepping experience replay with HER-style relabeling and rfaab sampling, improving learning speed and stability in sparse-reward mazes.