Backdoor Toy Adaptive Sprint

Fresh

Toy backdoor reward-hacking environment with fixed, ARW, WPO, and smoothed WPO reward variants

Type: RL Env
Tags: Reward Hacking Backdoor Adaptive Rewards
License: unknown
Size: v0.1.4
Published: May 2026
Updated: May 2026
Canonical: app.primeintellect.ai/dashboard/environments/shyampathak/backdoor-toy-adaptive-sprint

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/shyampathak/backdoor-toy-adaptive-sprint/@0.1.4/inspect

Attribution policy →

Contributors

1