paper-with-me

홈 › Papers

ConQUR: Mitigating Delusional Bias in Deep Q-learning

2020-02-27 · ICML 2020 1 · Andy Su, Jayden Ooi, Tyler Lu, Dale Schuurmans, Craig Boutilier

Delusional bias is a fundamental source of error in approximate Q-learning. To date, the only techniques that explicitly address delusion require comprehensive search using tabular value estimates. In this paper, we develop efficient methods to mitigate delusional bias by training Q-approximators with labels that are "consistent" with the underlying greedy policy class. We introduce a simple penalization scheme that encourages Q-labels used across training batches to remain (jointly) consistent with the expressible policy class. We also propose a search framework that allows multiple Q-approximators to be generated and tracked, thus mitigating the effect of premature (implicit) policy commitments. Experimental results demonstrate that these methods can improve the performance of Q-learning in a variety of Atari games, sometimes dramatically.

📄 PDF Abstract BibTeX arXiv:2002.12399

Code (1)

BigHeaded2003/ConQUR-Mitigating-Delusional-Bias-in-Deep-Q-Learning tf

Tasks

Atari GamesQ-Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians

2026-02-22 · Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley, Joshua B. Tenenbaum arxiv

"AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in outlandish beliefs after extended chatbot conversations. This phenomenon is typically att…

Non-delusional Q-learning and value-iteration

2018-12-01 · NeurIPS 2018 12 · Tyler Lu, Dale Schuurmans, Craig Boutilier

We identify a fundamental source of error in Q-learning and other forms of dynamic programming with function approximation. Delusional bias arises when the approximation architecture limits the class of expressible greed…

Q-Learning

Lost in Delusion: Examining LLM Safety Under User Delusions and Distress

2026-05-31 · Andrew Aquilina, Chetna Nihalani, Vasudha Varadarajan, Nathan S. Fishbein 외 arxiv

LLM chatbots increasingly serve as a first source of support for people in psychological distress, including those whose distress is entangled with delusional beliefs. Prior work on LLM mental-health safety largely evalu…

The Delusional Hedge Algorithm as a Model of Human Learning from Diverse Opinions

2024-02-21 · Yun-Shiuan Chuang, Jerry Zhu, Timothy T. Rogers

Whereas cognitive models of learning often assume direct experience with both the features of an event and with a true label or outcome, much of everyday learning arises from hearing the opinions of others, without direc…

Rejecting Hallucinated State Targets during Planning

2024-10-09 · Mingde Zhao, Tristan Sylvain, Romain Laroche, Doina Precup 외

Generative models can be used in planning to propose targets corresponding to states that agents deem either likely or advantageous to experience. However, imperfections, common in learned models, lead to infeasible hall…

Decision MakingOut-of-Distribution Generalization