GenDa adds skill relabeling and CIB to unsupervised RL to reduce non-stationarity and boost generalization, claiming better data efficiency and scalability.
Neural Information Processing Systems (NeurIPS) , year =
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
-
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
GenDa adds skill relabeling and CIB to unsupervised RL to reduce non-stationarity and boost generalization, claiming better data efficiency and scalability.