Corpus ID: 53424488

Reward learning from human preferences and demonstrations in Atari

@inproceedings{Ibarz2018RewardLF,
  title={Reward learning from human preferences and demonstrations in Atari},
  author={Borja Ibarz and J. Leike and Tobias Pohlen and Geoffrey Irving and S. Legg and Dario Amodei},
  booktitle={NeurIPS},
  year={2018}
}

Borja Ibarz, J. Leike, +3 authors Dario Amodei

Published in NeurIPS 2018

Computer Science, Mathematics

To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. [...] Key Method We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games without using game rewards. Additionally, we investigate the goodness of fit of the reward model…Expand Abstract

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed