
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards
We propose a new complexity measure for Markov decision processes (MDP),...
read it

Nearoptimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities
We study modelbased reinforcement learning in an unknown finite communi...
read it

Nearoptimal Reinforcement Learning using Bayesian Quantiles
We study modelbased reinforcement learning in finite communicating Mark...
read it

Nearoptimal Regret Bounds for Stochastic Shortest Path
Stochastic shortest path (SSP) is a wellknown problem in planning and c...
read it

Solving MultiObjective MDP with Lexicographic Preference: An application to stochastic planning with multiple quantile objective
In most common settings of Markov Decision Process (MDP), an agent evalu...
read it

Insulin Regimen MLbased control for T2DM patients
We model individual T2DM patient blood glucose level (BGL) by stochasti...
read it

RewardBased Deception with Cognitive Bias
Deception plays a key role in adversarial or strategic interactions for ...
read it
Nearoptimal Bayesian Solution For Unknown Discrete Markov Decision Process
We tackle the problem of acting in an unknown finite and discrete Markov Decision Process (MDP) for which the expected shortest path from any state to any other state is bounded by a finite number D. An MDP consists of S states and A possible actions per state. Upon choosing an action a_t at state s_t, one receives a real value reward r_t, then one transits to a next state s_t+1. The reward r_t is generated from a fixed reward distribution depending only on (s_t, a_t) and similarly, the next state s_t+1 is generated from a fixed transition distribution depending only on (s_t, a_t). The objective is to maximize the accumulated rewards after T interactions. In this paper, we consider the case where the reward distributions, the transitions, T and D are all unknown. We derive the first polynomial time Bayesian algorithm, BUCRL that achieves up to logarithm factors, a regret (i.e the difference between the accumulated rewards of the optimal policy and our algorithm) of the optimal order Õ(√(DSAT)). Importantly, our result holds with high probability for the worstcase (frequentist) regret and not the weaker notion of Bayesian regret. We perform experiments in a variety of environments that demonstrate the superiority of our algorithm over previous techniques. Our work also illustrates several results that will be of independent interest. In particular, we derive a sharper upper bound for the KLdivergence of Bernoulli random variables. We also derive sharper upper and lower bounds for Beta and Binomial quantiles. All the bound are very simple and only use elementary functions.
READ FULL TEXT
Comments
There are no comments yet.