Search Results for author:
Found 5 papers, 0 papers with code
Approximate information state based convergence analysis of recurrent Q-learning
In spite of the large literature on reinforcement learning (RL) algorithms for partially observable Markov decision processes (POMDPs), a complete theoretical understanding is still lacking.
On learning Whittle index policy for restless bandits with scalable regret
In particular, we consider a restless bandit model, and propose a Thompson-sampling based learning algorithm which is tuned to the underlying structure of the model.
Two families of indexable partially observable restless bandits and Whittle index computation
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 second, the state of each bandit is observable only if it is chosen.
Conditions for indexability of restless bandits and an O(K^3) algorithm to compute Whittle index
We then revisit a previously proposed algorithm called adaptive greedy algorithm which is known to compute the Whittle index for a subclass of restless bandits.
Gambler's Ruin Bandit Problem
In the GRBP, the learner proceeds in a sequence of rounds, where each round is a Markov Decision Process (MDP) with two actions (arms): a continuation action that moves the learner randomly over the state space around the current state; and a terminal action that moves the learner directly into one of the two terminal states (goal and dead-end state).
