2.7k citations · 4k across the 84 of their papers we have counts for
7 papers · 1 filter
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Branislav Kveton, Csaba Szepesvari, Sharan Vaswani +3
We propose a bandit algorithm that explores by randomizing its history of rewards. Specifically, it pulls the arm with the highest mean reward in a non-parametric bootstrap sample…
A Block Coordinate Ascent Algorithm for Mean-Variance Optimization
Bo Liu, Tengyang Xie, Yangyang Xu +4
Risk management in dynamic decision problems is a primary concern in many fields, including financial investment, autonomous driving, and healthcare. The mean-variance function is…
Risk-Sensitive Generative Adversarial Imitation Learning
Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow +1
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imi…
A Lyapunov-based Approach to Safe Reinforcement Learning
Yinlam Chow, Ofir Nachum, Edgar Duenez-Guzman +1
In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In part…
Optimizing over a Restricted Policy Class in Markov Decision Processes
Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh +1
We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem…
Path Consistency Learning in Tsallis Entropy Regularized MDPs
Ofir Nachum, Yinlam Chow, Mohammad Ghavamzadeh
We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulat…
More Robust Doubly Robust Off-policy Evaluation
Mehrdad Farajtabar, Yinlam Chow, Mohammad Ghavamzadeh
We study the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of a policy from the data generated by another pol…