Deployed RL agents receiving evaluative rewards face inherent non-stationarity and should engage in continual learning rather than following a train-then-fix approach.
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
-
Position: Deployed Reinforcement Learning should be Continual
Deployed RL agents receiving evaluative rewards face inherent non-stationarity and should engage in continual learning rather than following a train-then-fix approach.