Aligning AI Agents via Information-Directed Sampling
원문 초록
The staggering feats of AI systems have brought to attention the topic of AI Alignment: aligning a "superintelligent" AI agent's actions with humanity's interests. Many existing frameworks/algorithms in alignment study the problem on a myopic horizon or study learning from human feedback in isolation, relying on the contrived assumption that the agent has already perfectly identified the environment. As a starting point to address these limitations, we define a class of bandit alignment problems as an extension of classic multi-armed bandit problems. A bandit alignment problem involves an agent tasked with maximizing long-run expected reward by interacting with an environment and a human, both involving details/preferences initially unknown to the agent. The reward of actions in the environment depends on both observed outcomes and human preferences. Furthermore, costs are associated with querying the human to learn preferences. Therefore, an effective agent ought to intelligently trade-off exploration (of the environment and human) and exploitation. We study these trade-offs theoretically and empirically in a toy bandit alignment problem which resembles the beta-Bernoulli bandit. We demonstrate while naive exploration algorithms which reflect current practices and even touted algorithms such as Thompson sampling both fail to provide acceptable solutions to this problem, information-directed sampling achieves favorable regret.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Representative Action Selection for Large Action-Space Meta-Bandits
Steering Generative Models with Experimental Data for Protein Fitness Optimization
Addressing Missing Data Issue for Diffusion-based Recommendation
Dynamic Assortment Selection and Pricing with Censored Preference Feedback
Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers
Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.