@inproceedings{SDlta18,
    author = {Matthew Saponaro and Keith Decker},
    title = {Partial Policy Re-use in Connected Health Systems},
    booktitle = {Proceedings of the AAAI Fall Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy},
    pages = {74--81},
    year = {2018},
    abstract = {We examine Probabilistic Partial Policy Reuse (PPR) for the purposes of developing tailored coaching strategies in the Coach-Trainee Problem (CTP). Policy reuse (PR) aims to improve a reinforcement learning agent by guiding exploration with past similar problems’ learned policies. PPR extends probabilistic policy reuse that transfers only relevant parts of a policy for new problems. We explore PPR in the context of a human CTP where a coaching agent must develop a coaching strategy for the human trainee in order for the trainee to efficiently solve their problem (e.g. lose weight). In human CTPs, coach training data is limited because collecting too much data may annoy/discourage/harm the human trainee. In this paper, we present a decision tree-based algorithm, DT-partition, to identify partitions in the state space based on the problem’s features, and also examine the effects of grouping problem meta-data (i.e. pruning the decision tree) on CTP performance. Particularly, we demonstrate that PPR improves task library generation and expert policy utilization compared with policy reuse.}
}