Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Policy Improvement on HalfCheetah (HC)

19Rate

DT

Updated 17d ago

Evaluation Results

Method	Links
DT 2026.07		19	2.6
ORCAID 2026.07		14	2.9

SOTA Paper

DT

ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies

Dataset

halfcheetah

Follow for update

@wizwand_team Discord

Related Benchmarks

Reinforcement Learning Surrogate Modeling on Pendulum (P) (test)Policy Improvement on InvertedPendulum (IP)Policy Improvement on InvertedDoublePendulum (IDP)Reinforcement Learning Surrogate Modeling on MountainCar (test)Reinforcement Learning Surrogate Modeling on LunarLander (LL) (test)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs