A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
Prior work on training generative Visual Dialog models with reinforcement learning (Das et al., 2017b) has explored a Q-BOT-A-BOT image-guessing game and shown that this 'self-talk' approach can lead to improved performance at the downstream dialogconditioned image-guessing task. However, this improvement saturates and starts degrading after a few rounds of interaction, and does not lead to a better Visual Dialog model. We find that this is due in part to repeated interactions between Q-BOT anddoi:10.18653/v1/d19-1152 dblp:conf/emnlp/MurahariCBPD19 fatcat:35dt2n4qa5govetclxcjw63kqe