Oblique decision trees with local linear models can approximate deep RL policies with continuous actions using far fewer parameters than axis-aligned trees while retaining task performance.
Verifiable reinforcement learning via policy extraction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
Oblique decision trees with local linear models can approximate deep RL policies with continuous actions using far fewer parameters than axis-aligned trees while retaining task performance.