Titlebook: Recent Advances in Reinforcement Learning; 9th European Worksho Scott Sanner,Marcus Hutter Conference proceedings 2012 Springer-Verlag Berl

CHYME

Robust Bayesian Reinforcement Learning through Tight Lower Boundses of interest, such as reinforcement learning problems. While utility bounds are known to exist for this problem, so far none of them were particularly tight. In this paper, we show how to efficiently calculate a lower bound, which corresponds to the utility of a near-optimal . policy for the decis

amplitude

Active Learning of MDP Modelsnt rewards to be used in the decision-making process. As computing the optimal Bayesian value function is intractable for large horizons, we use a simple algorithm to approximately solve this optimization problem. Despite the sub-optimality of this technique, we show experimentally that our proposal is efficient in a number of domains.

灌溉

Recursive Least-Squares Learning with Eligibility Tracessions of FPKF and GPTD/KTD. We describe their recursive implementation, discuss their convergence properties, and illustrate their behavior experimentally. Overall, our study suggests that the state-of-art LSTD(.) [21] remains the best least-squares algorithm.

團結

極少

表否定

Goal-Directed Online Learning of Predictive Models efficient. Our algorithm interleaves online learning of the models, with estimation of the value function. The framework is applicable to a variety of important learning problems, including scenarios such as apprenticeship learning, model customization, and decision-making in non-stationary domains.

緩解

Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Controlnd seems to come with empirical advantages. We further extend a previous gradient based algorithm to the case of full control, by using generalized policy iteration. Theoretical properties of these algorithms are studied in a companion paper.

Gum-Disease

Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metricse states in a small MDP and the states in a large MDP, which we want to solve. The . of this metric is then used to completely define a set of options for the large MDP. We demonstrate empirically that our approach is able to improve the speed of reinforcement learning, and is generally not sensitive to parameter tuning.

Tractable

約會

Value Function Approximation through Sparse Bayesian Modelingl strategy is adopted. A number of experiments have been conducted on both simulated and real environments, where we took promising results in comparison with another Bayesian approach that uses Gaussian processes.