IQL achieves policy improvement in offline RL by implicitly estimating optimal action values through state-conditional upper expectiles of value functions, without querying Q-functions on out-of-distribution actions.
In particular, we discuss connections to BCQ Fujimoto et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Offline Reinforcement Learning with Implicit Q-Learning
IQL achieves policy improvement in offline RL by implicitly estimating optimal action values through state-conditional upper expectiles of value functions, without querying Q-functions on out-of-distribution actions.