Regret Analysis of a Markov Policy Gradient Algorithm for Multi-arm Bandits
We consider a policy gradient algorithm applied to a finite-arm bandit problem with Bernoulli rewards. We allow learning rates to depend on the current state of the algorithm, rather than use a deterministic time-decreasing learning rate. The state of the algorithm forms a Markov chain on the probability simplex. We apply Foster-Lyapunov techniques to analyse the stability of this Markov chain. We prove that if learning rates are well chosen then the policy gradient algorithm is a transient Markov chain and the state of the chain converges on the optimal arm with logarithmic or poly-logarithmic regret.
Aug-5-2020
- Country:
- North America > United States
- California > Alameda County > Hayward (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- Genre:
- Research Report (0.50)