2.7k citations · 4k across the 84 of their papers we have counts for
62 papers · 1 filter
Bayesian policy gradient and actor-critic algorithms
Mohammad Ghavamzadeh, Yaakov Engel, Michal Valko
Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods u…
Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
Julien Audiffren, Michal Valko, Alessandro Lazaric +1
A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maxim…
Ordering-based Conditions for Global Convergence of Policy Gradient Methods
Jincheng Mei, Bo Dai, Alekh Agarwal +3
We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the pol…
Maximum Entropy Model Correction in Reinforcement Learning
Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh +1
We propose and theoretically analyze an approach for planning with an approximate model in reinforcement learning that can reduce the adverse impact of model error. If the model is…
Bayesian Regret Minimization in Offline Bandits
Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh
We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on…
Private and Communication-Efficient Algorithms for Entropy Estimation
Gecia Bravo-Hermsdorff, Róbert Busa-Fekete, Mohammad Ghavamzadeh +2
Modern statistical estimation is often performed in a distributed setting where each sample belongs to a single user who shares their data with a central server. Users are typicall…
DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
Ying Fan, Olivia Watkins, Yuqing Du +7
Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and the…
Aligning Text-to-Image Models using Human Feedback
Kimin Lee, Hao Liu, Moonkyung Ryu +6
Deep generative models have shown impressive results in text-to-image synthesis. However, current text-to-image models often generate images that are inadequately aligned with text…
Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management
Dhawal Gupta, Yinlam Chow, Aza Tulepbergenov +2
Reinforcement learning (RL) has shown great promise for developing dialogue management (DM) agents that are non-myopic, conduct rich conversations, and maximize overall user satisf…
Multi-Task Off-Policy Learning from Bandit Feedback
Joey Hong, Branislav Kveton, Sumeet Katariya +2
Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users…
Operator Splitting Value Iteration
Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh +1
We introduce new planning and reinforcement learning algorithms for discounted MDPs that utilize an approximate model of the environment to accelerate the convergence of the value…
RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk
Jia Lin Hau, Marek Petrik, Mohammad Ghavamzadeh +1
Prior work on safe Reinforcement Learning (RL) has studied risk-aversion to randomness in dynamics (aleatory) and to model uncertainty (epistemic) in isolation. We propose and anal…
Robust Reinforcement Learning using Offline Data
Kishan Panaganti, Zaiyan Xu, Dileep Kalathil +1
The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-w…
Collaborative Multi-agent Stochastic Linear Bandits
Ahmadreza Moradipari, Mohammad Ghavamzadeh, Mahnoosh Alizadeh
We study a collaborative multi-agent stochastic linear bandit setting, where agents that form a network communicate locally to minimize their overall regret. In this setting, e…
Multi-Environment Meta-Learning in Stochastic Linear Bandits
Ahmadreza Moradipari, Mohammad Ghavamzadeh, Taha Rajabzadeh +2
In this work we investigate meta-learning (or learning-to-learn) approaches in multi-task linear stochastic bandit problems that can originate from multiple environments. Inspired…
Efficient Risk-Averse Reinforcement Learning
Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh +1
In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. A risk measure often focuses on the worst returns out of the agent's experienc…
Deep Hierarchy in Bandits
Joey Hong, Branislav Kveton, Sumeet Katariya +2
Mean rewards of actions are often correlated. The form of these correlations may be complex and unknown a priori, such as the preferences of a user for recommended products and the…
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
MohammadJavad Azizi, Thang Duong, Yasin Abbasi-Yadkori +3
We study a sequential decision problem where the learner faces a sequence of -armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unkno…
Meta-Learning for Simple Regret Minimization
Mohammadjavad Azizi, Branislav Kveton, Mohammad Ghavamzadeh +1
We develop a meta-learning framework for simple regret minimization in bandits. In this framework, a learning agent interacts with a sequence of bandit tasks, which are sampled i.i…
Hierarchical Bayesian Bandits
Joey Hong, Branislav Kveton, Manzil Zaheer +1
Meta-, multi-task, and federated learning can be all viewed as solving similar tasks, drawn from a distribution that reflects task similarities. We provide a unified view of all th…
Thompson Sampling with a Mixture Prior
Joey Hong, Branislav Kveton, Manzil Zaheer +2
We study Thompson sampling (TS) in online decision making, where the uncertain environment is sampled from a mixture distribution. This is relevant in multi-task learning, where a…
Feature and Parameter Selection in Stochastic Linear Bandits
Ahmadreza Moradipari, Berkay Turan, Yasin Abbasi-Yadkori +2
We study two model selection settings in stochastic linear bandits (LB). In the first setting, which we refer to as feature selection, the expected reward of the LB problem is in t…
Fixed-Budget Best-Arm Identification in Structured Bandits
Mohammad Javad Azizi, Branislav Kveton, Mohammad Ghavamzadeh
Best-arm identification (BAI) in a fixed-budget setting is a bandit problem where the learning agent maximizes the probability of identifying the optimal (best) arm after a fixed n…
Adaptive Sampling for Minimax Fair Classification
Shubhanshu Shekhar, Greg Fields, Mohammad Ghavamzadeh +1
Machine learning models trained on uncurated datasets can often end up adversely affecting inputs belonging to underrepresented groups. To address this issue, we consider the probl…