Empirically Verifying Hypotheses Using Reinforcement Learning
Artificial Intelligence
2020-06-30 v1 Machine Learning
Machine Learning
Abstract
This paper formulates hypothesis verification as an RL problem. Specifically, we aim to build an agent that, given a hypothesis about the dynamics of the world, can take actions to generate observations which can help predict whether the hypothesis is true or false. Existing RL algorithms fail to solve this task, even for simple environments. In order to train the agents, we exploit the underlying structure of many hypotheses, factorizing them as {pre-condition, action sequence, post-condition} triplets. By leveraging this structure we show that RL agents are able to succeed at the task. Furthermore, subsequent fine-tuning of the policies allows the agent to correctly verify hypotheses not amenable to the above factorization.
Cite
@article{arxiv.2006.15762,
title = {Empirically Verifying Hypotheses Using Reinforcement Learning},
author = {Kenneth Marino and Rob Fergus and Arthur Szlam and Abhinav Gupta},
journal= {arXiv preprint arXiv:2006.15762},
year = {2020}
}