… empiricallyanalyzed the performance of automated stock trading based on deep reinforcement learning … We conducted empiricalanalysis in three ways to determine whether it is …
… analysis of Expected Sarsa, a variation on Sarsa, the classic onpolicy temporal-difference method for model-free reinforcementlearning. Expected Sarsa exploits knowledge about …
… reinforcementlearning tasks. While both classes of methods benefit from independent theoretical analyses, … We conduct an empirical study to examine the strengths and weaknesses of …
… For our purposes, the final outcome resulting from a reinforcementlearning algorithm is a policy. … reinforcementlearning from two different levels. First, defining reinforcementlearning as …
… , and we believe that by identifying, replicating and solving these challenges, reinforcement learning can be more readily used to solve many of these important real-world problems. …
… learning. This paper undertakes a detailed examination of average reward reinforcement learning… , adaptive control, learning automata, and reinforcementlearning. A general optimality …
SJ Gershman - Journal of Mathematical Psychology, 2016 - Elsevier
… Computational models of reinforcementlearning have played an important role in understanding learning and decision making behavior, as well as the neural mechanisms underlying …
M Lopes, T Lang, M Toussaint… - Advances in neural …, 2012 - proceedings.neurips.cc
… motivation [10, 13, 12] and has shown empirical success in developmental robotics [1]. An … on empirical measures of learning progress to drive exploration in reinforcementlearning [17, …
M Grzes, D Kudenko - … Conference on Machine Learning and …, 2009 - ieeexplore.ieee.org
… Reinforcementlearning suffers scalability problems due to the state space explosion and … domain knowledge into reinforcementlearning. Theoretical and empiricalanalysis of this …