Machine Learning Proceedings 1995 PDF Download

Abstract: "The workshop on Value Function Approximation took place at the 1995 Machine Learning Conference in Tahoe City, California. It explored the issues that arise in reinforcement learning when the value function cannot be learned exactly, but must be approximated. It has long been recognized that approximation is essential on large, real-world problems because the state space is too large to permit table-lookup approaches. In addition, we need to generalize from past experiences to future ones, which inevitably involves making approximations. In principle, all methods for learning from examples are relevant here, but in practice only a few have been tried, and fewer still have been effective. This workshop brought together all the strands of reinforcement learning research that bear directly on the issue of value function approximation in reinforcement learning. We surveyed what works and what doesn't, and achieved a better understanding of what makes value function approximaton special as a learning from examples problem."