English
Related papers

Related papers: Mitigating Goal Misgeneralization via Minimax Regr…

200 papers

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret is a commonly used objective that theoretically results in…

Machine Learning · Computer Science 2024-06-11 Michael Beukman , Samuel Coward , Michael Matthews , Mattie Fellows , Minqi Jiang , Michael Dennis , Jakob Foerster

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…

Machine Learning · Computer Science 2025-07-09 Lukas Fluri , Leon Lang , Alessandro Abate , Patrick Forré , David Krueger , Joar Skalse

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Machine Learning · Computer Science 2024-01-17 Houda Nait El Barj , Theophile Sautory

While reinforcement learning (RL) agents often perform well during training, they can struggle with distribution shift in real-world deployments. One particularly severe risk of distribution shift is goal misgeneralization, where the agent…

Machine Learning · Computer Science 2024-11-12 Tu Trinh , Mohamad H. Danesh , Nguyen X. Khanh , Benjamin Plaut

In safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcomes rather than expected reward. We prove the first regret…

Machine Learning · Computer Science 2022-10-12 O. Bastani , Y. J. Ma , E. Shen , W. Xu

We study agents acting in an unknown environment where the agent's goal is to find a robust policy. We consider robust policies as policies that achieve high cumulative rewards for all possible environments. To this end, we consider agents…

Machine Learning · Computer Science 2024-10-22 Raghav Bongole , Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong…

Machine Learning · Computer Science 2023-01-11 Lauro Langosco , Jack Koch , Lee Sharkey , Jacob Pfau , Laurent Orseau , David Krueger

The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of…

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

Machine Learning · Computer Science 2024-10-31 Alexander Rutherford , Michael Beukman , Timon Willi , Bruno Lacerda , Nick Hawes , Jakob Foerster

To generalize the model trained in source domains to unseen target domains, domain generalization (DG) has recently attracted lots of attention. Since target domains can not be involved in training, overfitting source domains is inevitable.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Jian Zhang , Lei Qi , Yinghuan Shi , Yang Gao

This paper addresses the problem of universal learning under model misspecification with log-loss. In this setting, the learner operates with a hypothesis class of models denoted by $\Theta$, while the true data-generating process belongs…

Information Theory · Computer Science 2026-05-12 Shlomi Vituri , Meir Feder

Unsupervised Environment Design (UED) seeks to automatically generate training curricula for reinforcement learning (RL) agents, with the goal of improving generalisation and zero-shot performance. However, designing effective curricula…

Machine Learning · Computer Science 2026-01-22 Harry Mead , Bruno Lacerda , Jakob Foerster , Nick Hawes

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

Machine Learning · Computer Science 2021-03-01 Naman Agarwal , Elad Hazan , Anirudha Majumdar , Karan Singh

Modern complex datasets often consist of various sub-populations with known group information. In the presence of sub-population heterogeneity, it is crucial to develop robust and generalizable learning methods that (1) can enjoy robust…

Methodology · Statistics 2025-09-30 Weibin Mo , Weijing Tang , Songkai Xue , Yufeng Liu , Ji Zhu

Many machine learning tasks can be formulated as Regularized Empirical Risk Minimization (R-ERM), and solved by optimization algorithms such as gradient descent (GD), stochastic gradient descent (SGD), and stochastic variance reduction…

Machine Learning · Statistics 2016-09-28 Qi Meng , Yue Wang , Wei Chen , Taifeng Wang , Zhi-Ming Ma , Tie-Yan Liu

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…

Machine Learning · Computer Science 2023-06-30 Haotian Ye , Xiaoyu Chen , Liwei Wang , Simon S. Du

Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which is characterized by learning everything presented in the…

Machine Learning · Computer Science 2024-07-16 Zongbo Han , Yifeng Yang , Changqing Zhang , Linjun Zhang , Joey Tianyi Zhou , Qinghua Hu

In this paper, we consider learning scenarios where the learned model is evaluated under an unknown test distribution which potentially differs from the training distribution (i.e. distribution shift). The learner has access to a family of…

Machine Learning · Computer Science 2022-02-14 Alekh Agarwal , Tong Zhang

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

Machine Learning · Computer Science 2020-05-26 Rui Zhao , Xudong Sun , Volker Tresp
‹ Prev 1 2 3 10 Next ›