Abstract:
This article discusses the family of Newcomblike problems in the context of reinforcement learning. This reframes the problem of rational decision making as one of obtaining maximal rewards in a wide range of environments. Newcomblike problems are characterized by correlations between agent and environment policies. Such correlations are likely if the environment contains other agents with similar architectures, which is a realistic assumption in practice. An optimal policy, taking into account these correlations, is given for known environments.
Enjoy.
No comments:
Post a Comment