In this work, we propose an information-directed objective for infinite-horizon reinforcement learning (RL), called the occupancy information ratio (OIR), inspired by the information ratio objectives used in previous information-directed sampling schemes for multi-armed bandits and Markov decision processes as well as recent advances in general utility RL. The OIR, comprised of a ratio between the average cost of a policy and the entropy of its induced state occupancy measure, enjoys rich underlying structure and presents an objective to which scalable, model-free policy search methods naturally apply. Specifically, we show by leveraging connections between quasiconcave optimization and the linear programming theory for Markov decision processes that the OIR problem can be transformed and solved via concave programming methods when the underlying model is known. Since model knowledge is typically lacking in practice, we lay the foundations for model-free OIR policy search methods by establishing a corresponding policy gradient theorem. Building on this result, we subsequently derive REINFORCE- and actor-critic-style algorithms for solving the OIR problem in policy parameter space. Crucially, exploiting the powerful hidden quasiconcavity property implied by the concave programming transformation of the OIR problem, we establish finite-time convergence of the REINFORCE-style scheme to global optimality and asymptotic convergence of the actor-critic-style scheme to (near) global optimality under suitable conditions. Finally, we experimentally illustrate the utility of OIR-based methods over vanilla methods in sparse-reward settings, supporting the OIR as an alternative to existing RL objectives.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Raleigh County records that date back to the founding of the county in 1850 are being newly preserved by county officials. Deputy Circuit Clerk Vickie Suttle said the "preservation of history" started about five years ago when former Raleigh County Circuit Clerk Paul Flanagan purchased a large document scanner that she affectionately calls "The Beast," because of its size. The machine resembles a large desk and has a conveyor-like belt at one end that feeds documents through a scanner.

You wake up, pour a cup of coffee, and eventually make your way to one or more crossword puzzles, word games and other brain twisters. The test of banked knowledge and problem-solving ability can boost your ego, or deflate it. It's the "use it or lose it" theory in action, and as I get older, I'd like to believe these mental exercises can help keep my mind sharp and maybe even ward off memory loss, even if my wife usually beats me at all these games. But is there any science behind that, or is it wishful thinking? I am trying to solve that riddle, because since launching the Golden State column two months ago, I've heard from a lot of readers who -- like me --put at least a bit of faith in the value of mental gymnastics.