Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration
Nov 07, 2017 (modified: Nov 07, 2017)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Reinforcement learning (RL) agents improve through trial-and-error, but when re- ward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notable problem in training deep RL agents to perform web-based tasks, such as booking flights or replying emails, where a single mis- take can ruin the entire sequence of actions. A common remedy is to “warm-start” the agent by pre-training it to mimic expert demonstrations, but this is prone to overfitting. Instead, we propose to constrain exploration using demonstrations. From each demonstration, we induce high-level “workflows” which constrain the allowable actions at each time step to be similar to those in the demonstration (e.g., “Step 1: click on a textbox; Step 2: enter some text”). Our exploration pol- icy then learns to identify successful workflows and samples actions that satisfy these workflows. Workflows prune out bad exploration directions and accelerate the agent’s ability to discover rewards. We use our approach to train a novel neural policy designed to handle the semi-structured nature of websites, and evaluate on a suite of web tasks, including the recent World of Bits benchmark. We achieve new state-of-the-art results, and show that workflow-guided exploration improves sample efficiency over behavioral cloning by more than 10x.
TL;DR:We solve the sparse rewards problem on web UI tasks using exploration guided by demonstrations