Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation

Josiah Hanna, Peter Stone, and Scott Niekum. Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation. In Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2017.

Download

[PDF]663.8kB  [postscript]572.6kB  [slides.pdf]1.3MB  

Abstract

For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current methods for exact high confidence off-policy evaluation that use importance sampling require a substantial amount of data to achieve a tight lower bound. Existing model-based methods only address the problem in discrete state spaces. Since exact bounds are intractable for many domains we trade off strict guarantees of safety for more data-efficient approximate bounds. In this context, we propose two bootstrapping off-policy evaluation methods which use learned MDP transition models in order to estimate lower confidence bounds on policy performance with limited data in both continuous and discrete state spaces. Since direct use of a model may introduce bias, we derive a theoretical upper bound on model bias for when the model transition function is estimated with i.i.d. trajectories. This bound broadens our understanding of the conditions under which model-based methods have high bias. Finally, we empirically evaluate our proposed methods and analyze the settings in which different bootstrapping off-policy confidence interval methods succeed and fail.

BibTeX Entry

@InProceedings{AAMAS17-Hanna,
  author = {Josiah Hanna and Peter Stone and Scott Niekum},
  title = {Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation},
  booktitle = {Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)},
  location = {Sao Paolo, Brazil},
  month = {May},
  year = {2017},
  abstract = {
    For an autonomous agent, executing a poor policy may be costly or even
      dangerous. For such agents, it is desirable to determine confidence
      interval lower bounds on the performance of any given policy without
      executing said policy. Current methods for exact high confidence off-policy
      evaluation that use importance sampling require a substantial amount of
      data to achieve a tight lower bound. Existing model-based methods only
      address the problem in discrete state spaces. Since exact bounds are
      intractable for many domains we trade off strict guarantees of safety for
      more data-efficient approximate bounds. In this context, we propose two
      bootstrapping off-policy evaluation methods which use learned MDP
      transition models in order to estimate lower confidence bounds on policy
      performance with limited data in both continuous and discrete state spaces.
      Since direct use of a model may introduce bias, we derive a theoretical
      upper bound on model bias for when the model transition function is
      estimated with i.i.d. trajectories. This bound broadens our understanding
      of the conditions under which model-based methods have high bias. Finally,
      we empirically evaluate our proposed methods and analyze the settings in
      which different bootstrapping off-policy confidence interval methods
      succeed and fail.
  },
}

Generated by bib2html.pl (written by Patrick Riley ) on Fri Jun 14, 2019 11:36:26