RNN agents trained via policy gradient exhibit state aliasing when multiple states share the same optimal action, unlike value-based methods.
Deep reinforcement learning with a natural language action space
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Study of State Aliasing in Structured Prediction with RNNs
RNN agents trained via policy gradient exhibit state aliasing when multiple states share the same optimal action, unlike value-based methods.