English
Related papers

Related papers: Interpolating Between Softmax Policy Gradient and …

200 papers

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap…

Machine Learning · Computer Science 2026-05-29 Christoph Dann , Yishay Mansour , Mehryar Mohri

This paper studies how to efficiently update the saddle-point strategy, or security strategy of one player in a matrix game when the other player develops new actions in the game. It is well known that the saddle-point strategy of one…

Computer Science and Game Theory · Computer Science 2017-11-08 Lichun Li , Cedric Langbort

We introduce the ``soft Deep MaxPain'' (softDMP) algorithm, which integrates the optimization of long-term policy entropy into reward-punishment reinforcement learning objectives. Our motivation is to facilitate a smoother variation of…

Machine Learning · Computer Science 2024-09-16 Jiexin Wang , Eiji Uchibe

Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a Conservative Update Policy algorithm with a theoretical…

Machine Learning · Computer Science 2022-02-16 Long Yang , Jiaming Ji , Juntao Dai , Yu Zhang , Pengfei Li , Gang Pan

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this…

Machine Learning · Computer Science 2018-06-13 Krzysztof Choromanski , Mark Rowland , Vikas Sindhwani , Richard E. Turner , Adrian Weller

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only…

We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications…

Machine Learning · Computer Science 2019-05-17 Wang Chi Cheung

Neural ranking models (NRMs) have shown remarkable success in recent years, especially with pre-trained language models. However, deep neural models are notorious for their vulnerability to adversarial examples. Adversarial attacks may…

Information Retrieval · Computer Science 2022-06-09 Chen Wu , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

This work investigates the use of Neural implicit representations, specifically Neural Radiance Fields (NeRF), for geometrical queries and motion planning. We show that by adding the capacity to infer occupancy in a radius to a pre-trained…

Robotics · Computer Science 2022-05-04 Michael Pantic , Cesar Cadena , Roland Siegwart , Lionel Ott

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features of the observations…

Machine Learning · Computer Science 2018-10-31 Yuri Burda , Harrison Edwards , Amos Storkey , Oleg Klimov

Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajectories with deep…

Machine Learning · Computer Science 2023-05-17 Toru Lin , Allan Jabri

We present a novel 3D mapping method leveraging the recent progress in neural implicit representation for 3D reconstruction. Most existing state-of-the-art neural implicit representation methods are limited to object-level reconstructions…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Stefan Lionar , Lukas Schmid , Cesar Cadena , Roland Siegwart , Andrei Cramariuc

Diversity-based approaches have recently gained popularity as an alternative paradigm to performance-based policy search. A popular approach from this family, Quality-Diversity (QD), maintains a collection of high-performing policies…

Machine Learning · Computer Science 2020-12-17 Nemanja Rakicevic , Antoine Cully , Petar Kormushev

Implicit regularization is an important way to interpret neural networks. Recent theory starts to explain implicit regularization with the model of deep matrix factorization (DMF) and analyze the trajectory of discrete gradient dynamics in…

Machine Learning · Computer Science 2023-08-14 Jian Cao , Chen Qian , Yihui Huang , Dicheng Chen , Yuncheng Gao , Jiyang Dong , Di Guo , Xiaobo Qu

In this paper, we propose a new Deep Neural Network (DNN) testing algorithm called the Constrained Gradient Descent (CGD) method, and an implementation we call CGDTest aimed at exposing security and robustness issues such as adversarial…

Machine Learning · Computer Science 2023-04-05 Vineel Nagisetty , Laura Graves , Guanting Pan , Piyush Jha , Vijay Ganesh

Natural gradient descent (NGD) is a powerful optimization technique for machine learning, but the computational complexity of the inverse Fisher information matrix limits its application in training deep neural networks. To overcome this…

Machine Learning · Computer Science 2024-12-11 Weihua Liu , Said Boumaraf , Jianwu Li , Chaochao Lin , Xiabi Liu , Lijuan Niu , Naoufel Werghi

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human…

Machine Learning · Computer Science 2021-06-23 Zaynah Javed , Daniel S. Brown , Satvik Sharma , Jerry Zhu , Ashwin Balakrishna , Marek Petrik , Anca D. Dragan , Ken Goldberg

The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic analysis or voting, face a trade-off between high computational cost and limited robustness under…

Cryptography and Security · Computer Science 2026-05-20 Chengcai Gao , Zhihong Sun , Xiaochuan Shi , Qiufeng Wang , Chao Liang