Re-weighted targeting enables provably beneficial transfer learning for deep Q-learning in non-stationary finite-horizon MDPs when reward differences are smoother than the Q-functions.
We now use the peeling argument to extend to uniform r
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Transfer $Q$-Learning for Offline Non-Stationary Reinforcement Learning
Re-weighted targeting enables provably beneficial transfer learning for deep Q-learning in non-stationary finite-horizon MDPs when reward differences are smoother than the Q-functions.