We explore approximate policy iteration (API), replacing the usual costfunction learning step with a learning step in policy space. We give policy-language biases that enable solution of very large relational Markov decision processes (MDPs) that no previous technique can solve. In particular, we induce high-quality domain-specific planners for classical planning domains (both deterministic and...

In traditional studies of language policy in China, scholars mainly try to evaluate language policy’s effectiveness in attaining goals such as national unity, economic development, and illiteracy reduction. Few people question the underlying framework of such language planning. This paper tries to call into question those basic assumptions. By adopting a critical theory perspective, this paper ...

We explore approximate policy iteration (API), replacing the usual costfunction learning step with a learning step in policy space. We give policy-language biases that enable solution of very large relational Markov decision processes (MDPs) that no previous technique can solve. In particular, we induce high-quality domain-specific planners for classical planning domains (both deterministic and...