English
Related papers

Related papers: Real-Time Parallel Counterfactual Regret Minimizat…

200 papers

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

Machine Learning · Computer Science 2024-12-10 Rohan Deb , Mohammad Ghavamzadeh , Arindam Banerjee

The Colonel Blotto game is a renowned resource allocation problem with a long-standing literature in game theory (almost 100 years). However, its scope of application is still restricted by the lack of studies on the incomplete-information…

Computer Science and Game Theory · Computer Science 2019-09-12 Dong Quan Vu , Patrick Loiseau , Alonso Silva

Simple adaptive procedures that converge to correlated equilibria are known to exist for normal form games (Hart and Mas-Colell 2000), but no such analogue exists for extensive-form games. Leveraging inspiration from Zinkevich et al.…

Computer Science and Game Theory · Computer Science 2022-07-15 Hugh Zhang

The framework of deep reinforcement learning (DRL) provides a powerful and widely applicable mathematical formalization for sequential decision-making. This paper present a novel DRL framework, termed \emph{$f$-Divergence Reinforcement…

Machine Learning · Computer Science 2021-12-15 Chen Gong , Qiang He , Yunpeng Bai , Zhou Yang , Xiaoyu Chen , Xinwen Hou , Xianjie Zhang , Yu Liu , Guoliang Fan

There has been significant recent progress in algorithms for approximation of Nash equilibrium in large two-player zero-sum imperfect-information games and exact computation of Nash equilibrium in multiplayer strategic-form games. While…

Computer Science and Game Theory · Computer Science 2025-10-01 Sam Ganzfried

Optimization has been widely used to generate smooth trajectories for motion planning. However, existing trajectory optimization methods show weakness when dealing with large-scale long trajectories. Recent advances in parallel computing…

Robotics · Computer Science 2025-07-18 Jiajun Yu , Nanhe Chen , Guodong Liu , Chao Xu , Fei Gao , Yanjun Cao

Most existing results about \emph{last-iterate convergence} of learning dynamics are limited to two-player zero-sum games, and only apply under rigid assumptions about what dynamics the players follow. In this paper we provide new results…

Computer Science and Game Theory · Computer Science 2022-03-24 Ioannis Anagnostides , Ioannis Panageas , Gabriele Farina , Tuomas Sandholm

We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in…

Computer Science and Game Theory · Computer Science 2015-12-14 Vasilis Syrgkanis , Alekh Agarwal , Haipeng Luo , Robert E. Schapire

We compare performance of the genetic algorithm and the counterfactual regret minimization algorithm in computing the near-equilibrium strategies in the simplified poker games. We focus on the von Neumann poker and the simplified version of…

Computer Science and Game Theory · Computer Science 2018-05-24 Mikhail Goykhman

In this paper, we investigate offline and online algorithms for rufpp, the problem of minimizing the number of rounds required to schedule a set of unsplittable flows of non-uniform sizes on a given path with non-uniform edge capacities.…

Data Structures and Algorithms · Computer Science 2017-08-02 Hamidreza Jahanjou , Erez Kantor , Rajmohan Rajaraman

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging…

Machine Learning · Computer Science 2024-06-19 Haque Ishfaq , Yixin Tan , Yu Yang , Qingfeng Lan , Jianfeng Lu , A. Rupam Mahmood , Doina Precup , Pan Xu

The rapid advancement of GPU technology has unlocked powerful parallel processing capabilities, creating new opportunities to enhance classic search algorithms. This hardware has been exploited in best-first search algorithms with neural…

Artificial Intelligence · Computer Science 2025-11-18 Ehsan Futuhi , Nathan R. Sturtevant

Follow-The-Regularized-Leader (FTRL) algorithms often enjoy optimal regret for adversarial as well as stochastic bandit problems and allow for a streamlined analysis. Nonetheless, FTRL algorithms require the solution of an optimization…

Machine Learning · Computer Science 2025-02-14 Mengmeng Li , Daniel Kuhn , Bahar Taşkesen

Classic no-regret multi-armed bandit algorithms, including the Upper Confidence Bound (UCB), Hedge, and EXP3, are inherently unfair by design. Their unfairness stems from their objective of playing the most rewarding arm as frequently as…

Machine Learning · Computer Science 2024-05-14 Abhishek Sinha

We propose efficient no-regret learning dynamics and ellipsoid-based methods for computing linear correlated equilibria$\unicode{x2014}$a relaxation of correlated equilibria and a strengthening of coarse correlated…

Computer Science and Game Theory · Computer Science 2024-12-31 Constantinos Daskalakis , Gabriele Farina , Maxwell Fishelson , Charilaos Pipis , Jon Schneider

We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a…

Machine Learning · Computer Science 2015-05-22 Adith Swaminathan , Thorsten Joachims

Contextual sequential decision-making problems play a crucial role in machine learning, encompassing a wide range of downstream applications such as bandits, sequential hypothesis testing and online risk control. These applications often…

Machine Learning · Statistics 2025-01-31 Haichen Hu , Rui Ai , Stephen Bates , David Simchi-Levi

Existing online learning algorithms for adversarial Markov Decision Processes achieve ${O}(\sqrt{T})$ regret after $T$ rounds of interactions even if the loss functions are chosen arbitrarily by an adversary, with the caveat that the…

Machine Learning · Computer Science 2023-10-27 Tiancheng Jin , Junyan Liu , Chloé Rouyer , William Chang , Chen-Yu Wei , Haipeng Luo

The PC algorithm is the state-of-the-art algorithm for causal structure discovery on observational data. It can be computationally expensive in the worst case due to the conditional independence tests are performed in an…

Machine Learning · Computer Science 2021-09-13 Kai Zhang , Chao Tian , Kun Zhang , Todd Johnson , Xiaoqian Jiang

Existing studies on provably efficient algorithms for Markov games (MGs) almost exclusively build on the "optimism in the face of uncertainty" (OFU) principle. This work focuses on a different approach of posterior sampling, which is…

Machine Learning · Computer Science 2022-10-06 Wei Xiong , Han Zhong , Chengshuai Shi , Cong Shen , Tong Zhang
‹ Prev 1 8 9 10 Next ›