HYDRO combines a small offline robust RL dataset with a mismatched online simulator, filtering simulator samples by uncertainty and gap to the worst-case model to improve robust policy performance.
Morel: Model-based offline reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hybrid Cross-domain Robust Reinforcement Learning
HYDRO combines a small offline robust RL dataset with a mismatched online simulator, filtering simulator samples by uncertainty and gap to the worst-case model to improve robust policy performance.