Rahul Meshram

Rahul Meshram, D. Manjunath, Aditya Gopalan

We consider a restless multi-armed bandit in which each arm can be in one of two states. When an arm is sampled, the state of the arm is not available to the sampler. Instead, a binary signal with a known randomness that depends on the state of the arm is available. No signal is available if the arm is not sampled. An arm-dependent reward is accrued from each sampling. In each time step, each arm changes state according to known transition probabilities which in turn depend on whether the arm is sampled or not sampled. Since the state of the arm is never visible and has to be inferred from the current belief and a possible binary signal, we call this the hidden Markov bandit. Our interest is in a policy to select the arm(s) in each time step that maximizes the infinite horizon discounted reward. Specifically, we seek the use of Whittle's index in selecting the arms. We first analyze the single-armed bandit and show that in general, it admits an approximate threshold-type optimal policy when there is a positive reward for the `no-sample' action. We also identify several special cases for which the threshold policy is indeed the optimal policy. Next, we show that such a single-armed bandit also satisfies an approximate-indexability property. For the case when the single-armed bandit admits a threshold-type optimal policy, we perform the calculation of the Whittle index for each arm. Numerical examples illustrate the analytical results.

Rahul Meshram, Aditya Gopalan, D. Manjunath

We consider a restless multi-armed bandit (RMAB) in which there are two types of arms, say A and B. Each arm can be in one of two states, say $0$ or $1.$ Playing a type A arm brings it to state $0$ with probability one and not playing it induces state transitions with arm-dependent probabilities. Whereas playing a type B arm leads it to state $1$ with probability $1$ and not playing it gets state that dependent on transition probabilities of arm. Further, play of an arm generates a unit reward with a probability that depends on the state of the arm. The belief about the state of the arm can be calculated using a Bayesian update after every play. This RMAB has been designed for use in recommendation systems where the user's preferences depend on the history of recommendations. This RMAB can also be used in applications like creating of playlists or placement of advertisements. In this paper we formulate the long term reward maximization problem as infinite horizon discounted reward and average reward problem. We analyse the RMAB by first studying discounted reward scenario. We show that it is Whittle-indexable and then obtain a closed form expression for the Whittle index for each arm calculated from the belief about its state and the parameters that describe the arm. We next analyse the average reward problem using vanishing discounted approach and derive the closed form expression for Whittle index. For a RMAB to be useful in practice, we need to be able to learn the parameters of the arms. We present an algorithm derived from Thompson sampling scheme, that learns the parameters of the arms and also illustrate its performance numerically.

Kesav Kaza, Rahul Meshram, Varun Mehta et al.

This work studies a generalized class of restless multi-armed bandits with hidden states and allow cumulative feedback, as opposed to the conventional instantaneous feedback. We call them lazy restless bandits (LRB) as the events of decision-making are sparser than events of state transition. Hence, feedback after each decision event is the cumulative effect of the following state transition events. The states of arms are hidden from the decision-maker and rewards for actions are state dependent. The decision-maker needs to choose one arm in each decision interval, such that long term cumulative reward is maximized. As the states are hidden, the decision-maker maintains and updates its belief about them. It is shown that LRBs admit an optimal policy which has threshold structure in belief space. The Whittle-index policy for solving LRB problem is analyzed; indexability of LRBs is shown. Further, closed-form index expressions are provided for two sets of special cases; for more general cases, an algorithm for index computation is provided. An extensive simulation study is presented; Whittle-index, modified Whittle-index and myopic policies are compared. Lagrangian relaxation of the problem provides an upper bound on the optimal value function; it is used to assess the degree of sub-optimality various policies.

Varun Mehta, Rahul Meshram, Kesav Kaza et al.

We study a problem of information gathering in a social network with dynamically available sources and time varying quality of information. We formulate this problem as a restless multi-armed bandit (RMAB). In this problem, information quality of a source corresponds to the state of an arm in RMAB. The decision making agent does not know the quality of information from sources a priori. But the agent maintains a belief about the quality of information from each source. This is a problem of RMAB with partially observable states. The objective of the agent is to gather relevant information efficiently from sources by contacting them. We formulate this as a infinite horizon discounted reward problem, where reward depends on quality of information. We study Whittle's index policy which determines the sequence of play of arms that maximizes long term cumulative reward. We illustrate the performance of index policy, myopic policy and compare with uniform random policy through numerical simulation.

Varun Mehta, Rahul Meshram, Kesav Kaza et al.

The problem of rested and restless multi-armed bandits with constrained availability of arms is considered. The states of arms evolve in Markovian manner and the exact states are hidden from the decision maker. First, some structural results on value functions are claimed. Following these results, the optimal policy turns out to be a \textit{threshold policy}. Further, \textit{indexability} of rested bandits is established and index formula is derived. The performance of index policy is illustrated and compared with myopic policy using numerical examples.

Parvish Kakarapalli, Devendra Kayande, Rahul Meshram

We study the Whittle index learning algorithm for restless multi-armed bandits (RMAB). We first present Q-learning algorithm and its variants -- speedy Q-learning (SQL), generalized speedy Q-learning (GSQL) and phase Q-learning (PhaseQL). We also discuss exploration policies -- $ε$-greedy and Upper confidence bound (UCB). We extend the study of Q-learning and its variants with UCB policy. We illustrate using numerical example that Q-learning with UCB exploration policy has faster convergence and PhaseQL with UCB have fastest convergence rate. We next extend the study of Q-learning variants for index learning to RMAB. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. We study constant stepsizes two timescale stochastic approximation algorithm. We describe the performance of our algorithms using numerical example. It illustrate that index learning with Q learning with UCB has faster convergence that $ε$ greedy. Further, PhaseQL (with UCB and $ε$ greedy) has the best convergence than other Q-learning algorithms.

Vishesh Mittal, Rahul Meshram, Surya Prakash

We study the Whittle index learning algorithm for restless multi-armed bandits. We consider index learning algorithm with Q-learning. We first present Q-learning algorithm with exploration policies -- epsilon-greedy, softmax, epsilon-softmax with constant stepsizes. We extend the study of Q-learning to index learning for single-armed restless bandit. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. In Q-learning updates are in asynchronous manner. We study constant stepsizes two timescale stochastic approximation algorithm. We provide analysis of two-timescale stochastic approximation for index learning with constant stepsizes. Further, we present study on index learning with deep Q-network (DQN) learning and linear function approximation with state-aggregation method. We describe the performance of our algorithms using numerical examples. We have shown that index learning with Q learning, DQN and function approximations learns the Whittle index.

Vishesh Mittal, Rahul Meshram, Deepak Dev et al.

We consider finite state restless multi-armed bandit problem. The decision maker can act on M bandits out of N bandits in each time step. The play of arm (active arm) yields state dependent rewards based on action and when the arm is not played, it also provides rewards based on the state and action. The objective of the decision maker is to maximize the infinite horizon discounted reward. The classical approach to restless bandits is Whittle index policy. In such policy, the M arms with highest indices are played at each time step. Here, one decouples the restless bandits problem by analyzing relaxed constrained restless bandits problem. Then by Lagrangian relaxation problem, one decouples restless bandits problem into N single-armed restless bandit problems. We analyze the single-armed restless bandit. In order to study the Whittle index policy, we show structural results on the single armed bandit model. We define indexability and show indexability in special cases. We propose an alternative approach to verify the indexable criteria for a single armed bandit model using value iteration algorithm. We demonstrate the performance of our algorithm with different examples. We provide insight on condition of indexability of restless bandits using different structural assumptions on transition probability and reward matrices. We also study online rollout policy and discuss the computation complexity of algorithm and compare that with complexity of index computation. Numerical examples illustrate that index policy and rollout policy performs better than myopic policy.

Rahul Meshram, Kesav Kaza

Partially observable restless multi-armed bandits have found numerous applications including in recommendation systems, communication systems, public healthcare outreach systems, and in operations research. We study multi-action partially observable restless multi-armed bandits, it is a generalization of the classical restless multi-armed bandit problem -- 1) each bandit has finite states, and the current state is not observable, 2) each bandit has finite actions. In particular, we assume that more than two actions are available for each bandit. We motivate our problem with the application of public-health intervention planning. We describe the model and formulate a long term discounted optimization problem, where the state of each bandit evolves according to a Markov process, and this evolution is action dependent. The state of a bandit is not observable but one of finitely many feedback signals are observable. Each bandit yields a reward, based on the action taken on that bandit. The agent is assumed to have a budget constraint. The bandits are assumed to be independent. However, they are weakly coupled at the agent through the budget constraint. We first analyze the Lagrangian bound method for our partially observable restless bandits. The computation of optimal value functions for finite-state, finite-action POMDPs is non-trivial. Hence, the computation of Lagrangian bounds is also challenging. We describe approximations for the computation of Lagrangian bounds using point based value iteration (PBVI) and online rollout policy. We further present various properties of the value functions and provide theoretical insights on PBVI and online rollout policy. We study heuristic policies for multi-actions PORMAB. Finally, we discuss present Whittle index policies and their limitations in our model.

Kesav Kaza, Ramachandran Anantharaman, Rahul Meshram

This paper introduces a two-timescale hierarchical decentralized control architecture for Cyber-Physical Systems (CPS). The system consists of a global controller (GC), and N local controllers (LCs). The GC operates at a slower timescale, imposing budget constraints on the actions of LCs, which function at a faster timescale. Applications can be found in energy grid planning, wildfire management, and other decentralized resource allocation problems. We propose and analyze two optimization frameworks for this setting: COpt and FOpt. In COpt, both GC and LCs together optimize infinite-horizon discounted rewards, while in FOpt the LCs optimize finite-horizon episodic rewards, and the GC optimizes infinite-horizon rewards. Although both frameworks share identical reward functions, their differing horizons can lead to different optimal policies. In particular, FOpt grants greater autonomy to LCs by allowing their policies to be determined only by local objectives, unlike COpt. To our knowledge, these frameworks have not been studied in the literature. We establish the formulations, prove the existence of optimal policies, and prove the convergence of their value iteration algorithms. We further show that COpt always achieves a higher value function than FOpt and derive explicit bounds on their difference. Finally, we establish a set of sufficient structural conditions under which the two frameworks become equivalent.

Rahul Meshram, Kesav Kaza

Restless multi-armed bandits with partially observable states has applications in communication systems, age of information and recommendation systems. In this paper, we study multi-state partially observable restless bandit models. We consider three different models based on information observable to decision maker -- 1) no information is observable from actions of a bandit 2) perfect information from bandit is observable only for one action on bandit, there is a fixed restart state, i.e., transition occurs from all other states to that state 3) perfect state information is available to decision maker for both actions on a bandit and there are two restart state for two actions. We develop the structural properties. We also show a threshold type policy and indexability for model 2 and 3. We present Monte Carlo (MC) rollout policy. We use it for whittle index computation in case of model 2. We obtain the concentration bound on value function in terms of horizon length and number of trajectories for MC rollout policy. We derive explicit index formula for model 3. We finally describe Monte Carlo rollout policy for model 1 when it is difficult to show indexability. We demonstrate the numerical examples using myopic policy, Monte Carlo rollout policy and Whittle index policy. We observe that Monte Carlo rollout policy is good competitive policy to myopic.

Rahul Meshram, Kesav Kaza

We model online recommendation systems using the hidden Markov multi-state restless multi-armed bandit problem. To solve this we present Monte Carlo rollout policy. We illustrate numerically that Monte Carlo rollout policy performs better than myopic policy for arbitrary transition dynamics with no specific structure. But, when some structure is imposed on the transition dynamics, myopic policy performs better than Monte Carlo rollout policy.

Rahul Meshram, Kesav Kaza

We consider multi-dimensional Markov decision processes and formulate a long term discounted reward optimization problem. Two simulation based algorithms---Monte Carlo rollout policy and parallel rollout policy are studied, and various properties for these policies are discussed. We next consider a restless multi-armed bandit (RMAB) with multi-dimensional state space and multi-actions bandit model. A standard RMAB consists of two actions for each arms whereas in multi-actions RMAB, there are more that two actions for each arms. A popular approach for RMAB is Whittle index based heuristic policy. Indexability is an important requirement to use index based policy. Based on this, an RMAB is classified into indexable or non-indexable bandits. Our interest is in the study of Monte-Carlo rollout policy for both indexable and non-indexable restless bandits. We first analyze a standard indexable RMAB (two-action model) and discuss an index based policy approach. We present approximate index computation algorithm using Monte-Carlo rollout policy. This algorithm's convergence is shown using two-timescale stochastic approximation scheme. Later, we analyze multi-actions indexable RMAB, and discuss the index based policy approach. We also study non-indexable RMAB for both standard and multi-actions bandits using Monte-Carlo rollout policy.

Kesav Kaza, Rahul Meshram, Varun Mehta et al.

This paper studies a class of constrained restless multi-armed bandits (CRMAB). The constraints are in the form of time varying set of actions (set of available arms). This variation can be either stochastic or semi-deterministic. Given a set of arms, a fixed number of them can be chosen to be played in each decision interval. The play of each arm yields a state dependent reward. The current states of arms are partially observable through binary feedback signals from arms that are played. The current availability of arms is fully observable. The objective is to maximize long term cumulative reward. The uncertainty about future availability of arms along with partial state information makes this objective challenging. Applications for CRMAB can be found in resource allocation in cyber-physical systems involving components with time varying availability. First, this optimization problem is analyzed using Whittle's index policy. To this end, a constrained restless single-armed bandit is studied. It is shown to admit a threshold-type optimal policy and is also indexable. An algorithm to compute Whittle's index is presented. An alternate solution method with lower complexity is also presented in the form of an online rollout policy. A detailed discussion on the complexity of both these schemes is also presented, which suggests that online rollout policy with short look ahead is simpler to implement than Whittle's index computation. Further, upper bounds on the value function are derived in order to estimate the degree of sub-optimality of various solutions. The simulation study compares the performance of Whittle's index, online rollout, myopic and modified Whittle's index policies.

Rahul Meshram, D. Manjunath, Nikhil Karamchandani

Personalized recommendation systems (RS) are extensively used in many services. Many of these are based on learning algorithms where the RS uses the recommendation history and the user response to learn an optimal strategy. Further, these algorithms are based on the assumption that the user interests are rigid. Specifically, they do not account for the effect of learning strategy on the evolution of the user interests. In this paper we develop influence models for a learning algorithm that is used to optimally recommend websites to web users. We adapt the model of \cite{Ioannidis10} to include an item-dependent reward to the RS from the suggestions that are accepted by the user. For this we first develop a static optimisation scheme when all the parameters are known. Next we develop a stochastic approximation based learning scheme for the RS to learn the optimal strategy when the user profiles are not known. Finally, we describe several user-influence models for the learning algorithm and analyze their effect on the steady user interests and on the steady state optimal strategy as compared to that when the users are not influenced.

Rahul Meshram, Aditya Gopalan, D. Manjunath

We describe and study a model for an Automated Online Recommendation System (AORS) in which a user's preferences can be time-dependent and can also depend on the history of past recommendations and play-outs. The three key features of the model that makes it more realistic compared to existing models for recommendation systems are (1) user preference is inherently latent, (2) current recommendations can affect future preferences, and (3) it allows for the development of learning algorithms with provable performance guarantees. The problem is cast as an average-cost restless multi-armed bandit for a given user, with an independent partially observable Markov decision process (POMDP) for each item of content. We analyze the POMDP for a single arm, describe its structural properties, and characterize its optimal policy. We then develop a Thompson sampling-based online reinforcement learning algorithm to learn the parameters of the model and optimize utility from the binary responses of the users to continuous recommendations. We then analyze the performance of the learning algorithm and characterize the regret. Illustrative numerical results and directions for extension to the restless hidden Markov multi-armed bandit problem are also presented.