A bound on OOD test performance in POMDPs decomposes loss into approximation and estimation errors, indicating that smaller abstract state spaces improve generalization in RL agents.
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
-
Smaller Abstract State Spaces Enable Cross-Scale Generalization in Reinforcement Learning
A bound on OOD test performance in POMDPs decomposes loss into approximation and estimation errors, indicating that smaller abstract state spaces improve generalization in RL agents.