Search Results for author:
Found 5 papers, 0 papers with code
Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation
To boost the learning loop, we propose SEER, an efficient PbRL method that integrates label smoothing and policy regularization techniques.
Efficient Model-agnostic Alignment via Bayesian Persuasion
This paper explores an efficient method for aligning black-box large models using smaller models, introducing a model-agnostic and lightweight Bayesian Persuasion Alignment framework.
Incentive Compatibility for AI Alignment in Sociotechnical Systems: Positions and Prospects
The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety.
Measuring Value Understanding in Language Models through Discriminator-Critique Gap
We argue that truly understanding values in LLMs requires considering both "know what" and "know why".
Zero-shot Preference Learning for Offline RL via Optimal Transport
In this paper, we propose a novel zero-shot preference-based RL algorithm that leverages labeled preference data from source tasks to infer labels for target tasks, eliminating the requirement for human queries.
