7 papers
Fair Resource Allocation in Weakly Coupled Markov Decision Processes
Xiaohui Tu, Yossiri Adulyasak, Nima Akbarzadeh +1
We consider fair resource allocation in sequential decision-making environments modeled as weakly coupled Markov decision processes, where resource constraints couple the action sp…
Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning
Nima Akbarzadeh, Yossiri Adulyasak, Erick Delage
In restless bandits, a central agent is tasked with optimally distributing limited resources across several bandits (arms), with each arm being a Markov decision process. In this w…
Approximate information state based convergence analysis of recurrent Q-learning
Erfan Seyedsalehi, Nima Akbarzadeh, Amit Sinha +1
In spite of the large literature on reinforcement learning (RL) algorithms for partially observable Markov decision processes (POMDPs), a complete theoretical understanding is stil…
On learning Whittle index policy for restless bandits with scalable regret
Nima Akbarzadeh, Aditya Mahajan
Reinforcement learning is an attractive approach to learn good resource allocation and scheduling policies based on data when the system model is unknown. However, the cumulative r…
Scalable Operator Allocation for Multi-Robot Assistance: A Restless Bandit Approach
Abhinav Dahiya, Nima Akbarzadeh, Aditya Mahajan +1
In this paper, we consider the problem of allocating human operators in a system with multiple semi-autonomous robots. Each robot is required to perform an independent sequence of…
Two families of indexable partially observable restless bandits and Whittle index computation
Nima Akbarzadeh, Aditya Mahajan
We consider the restless bandits with general state space under partial observability with two observational models: first, the state of each bandit is not observable at all, and s…
Gambler's Ruin Bandit Problem
Nima Akbarzadeh, Cem Tekin
In this paper, we propose a new multi-armed bandit problem called the Gambler's Ruin Bandit Problem (GRBP). In the GRBP, the learner proceeds in a sequence of rounds, where each ro…