paper-with-me

Papers

Provably Efficient Algorithms for Multi-Objective Competitive RL

2021-02-05 · Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra

We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell's approachability theorem (Blackwell, 1956) to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell's approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.

📄 PDF Abstract BibTeX arXiv:2102.03192

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Objective Reinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games

2024-06-06 · Jiawei Ge, Yuanhao Wang, Wenzhe Li, Chi Jin

This paper examines multiplayer symmetric constant-sum games with more than two players in a competitive setting, including examples like Mahjong, Poker, and various board and video games. In contrast to two-player zero-…

Archive-based Single-Objective Evolutionary Algorithms for Submodular Optimization

2024-06-19 · Frank Neumann, Günter Rudolph

Constrained submodular optimization problems play a key role in the area of combinatorial optimization as they capture many NP-hard optimization problems. So far, Pareto optimization approaches using multi-objective form…

Combinatorial OptimizationEvolutionary Algorithms

TS-RSR: A provably efficient approach for batch Bayesian Optimization

2024-03-07 · Zhaolin Ren, Na Li

This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling …

Bayesian OptimizationThompson Sampling

Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning

2021-02-22 · Lanqing Li, Yuanhao Huang, Mingzhe Chen, Siteng Luo 외

Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is to infer…

Contrastive LearningMeta-Learningreinforcement-learningReinforcement Learning (RL)+1

Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently

2020-02-26 · Ioannis Panageas, Stratis Skoulakis, Antonios Varvitsiotis, Xiao Wang

Non-negative matrix factorization (NMF) is a fundamental non-convex optimization problem with numerous applications in Machine Learning (music analysis, document clustering, speech-source separation etc). Despite having …

Clustering