Strategic Experimentation with Poisson Bandits

Strategic Experimentation with Poisson Bandits

We study a game of strategic experimentation with two-armed bandits where the risky arm distributes lump-sum payoffs according to a Poisson process. Its intensity is either high or low, and unknown to the players. We consider Markov perfect equilibria with beliefs as the state variable. As the belief process is piecewise deterministic, payoff functions solve differential-difference equations. T...

Godfrey Keller ; Sven Rady : Strategic Experimentation with Poisson Bandits

Strategic Experimentation with Exponential Bandits

This paper studies a game of strategic experimentation with two-armed bandits whose risky arm might yield a payoff only after some exponentially distributed random time. Because of free-riding, there is an inefficiently low level of experimentation in any equilibrium where the players use stationary Markovian strategies with posterior beliefs as the state variable. After characterizing the uniq...

Strategic Experimentation with Humped Bandits

Risks related to events that arrive randomly play important role in many real life decisions, and models of learning and experimentation based on twoarmed Poisson bandits addressed several important aspects related to strategic and motivational learning in cases when events arrive at jump times of the standard Poisson process. At the same time, these models fail to explain some interesting feat...

Strategic Experimentation with Congestion

We consider a multi-armed bandit model in which two players choose between learning about the quality of a risky option (modelled as a Poisson process with unknown arrival rate), and competing for the use of a single shared safe option that can only be used by one agent at the time. Firstly, when players cannot reverse their decision to switch to the safe option, the socially optimal policy mak...