7 items with this tag.12/23/2025Recontextualization Mitigates Specification Gaming Without Modifying the Specificationspecification gamingmats programAI12/18/20252025-Era “Reward Hacking” Does Not Show that Reward Is the Optimization Targetreinforcement learningspecification gamingAI11/22/2025Output Supervision Can Obfuscate the CoTreinforcement learningspecification gamingmats programAI6/19/2023Mode Collapse in RL May Be Fueled by the Update Equationreinforcement learningspecification gamingAI8/11/2022Seriously, What Goes Wrong with “Reward the Agent when It Makes You Smile”?specification gamingAI7/25/2022Reward Is Not the Optimization Targetreinforcement learningspecification gamingshard theoryAI9/13/2019What You See Isn’t Always What You Wantreinforcement learningspecification gamingAI