Empirically Verifying Hypotheses Using Reinforcement 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.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Visual Question Answering: Datasets, Algorithms, and Future Challenges
• Know What You Don't Know: Unanswerable Questions for SQuAD
• Gated-Attention Architectures for Task-Oriented Language Grounding
• Causal Reasoning from Meta-reinforcement Learning
• Learning to Perform Physics Experiments via Deep Reinforcement Learning
• Visual Question Answering: A Survey of Methods and Datasets
• Irreflexive and Hierarchical Relations as Translations
• Mixed Logical and Probabilistic Reasoning for Planning and Explanation Generation in Robotics