Author

Majid Ghasemi

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#reinforcement learning Oct 2026

Virtue by Observation: Social Reinforcement Learning for Intrinsically Ethical Agents

Reinforcement learning is increasingly deployed in settings with ethical stakes, yet rule-based and scalar-reward alignment approaches remain brittle and prone to proxy gaming. I argue that two of their most persistent failures, hallucination and moral drift, share a single structural cause, which I term \textit{feedba...

Majid Ghasemi · Proceedings of the AAAI/ACM... · 0 citations

#reinforcement learning Oct 2026

The Forager’s Dilemma: Peer Enforcement Alone Is Not Enough for Stable Multi-Agent Alignment

AI alignment methods typically rely on one of two strategies, either optimizing a scalar reward proxy learned from human feedback or situating agents in social environments where peer critique provides a dynamic correction signal. We argue that both strategies, taken in isolation, are structurally unstable. Static scal...

Majid Ghasemi, Prabhjyot Singh, Mark Crowley · Proceedings of the AAAI/ACM... · 0 citations

#reinforcement learning Oct 2026

AI Alignment Without Representation: From Scalar Rewards to Social Deliberation

Despite the widespread adoption of Reinforcement Learning from Human Feedback, state-of-the-art AI systems remain prone to two persistent failures. The first is hallucination, or the production of fluent but false content. The second is moral drift, or the convergence toward exploitative or harmful equilibria under sus...

Majid Ghasemi, Mark Crowley · Proceedings of the AAAI/ACM... · 0 citations