Develops symmetry-aware LSVI with invariant kernels for RL, derives bounds on information gain and covering numbers for invariant RKHSs, and shows empirical gains on Frozen Lake and 2D placement tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Reinforcement Learning Using known Invariances
Develops symmetry-aware LSVI with invariant kernels for RL, derives bounds on information gain and covering numbers for invariant RKHSs, and shows empirical gains on Frozen Lake and 2D placement tasks.