Search Results for author: Girish Sastry

Found 6 papers, 5 papers with code

Trial without Error: Towards Safe Reinforcement Learning via Human Intervention

1 code implementation17 Jul 2017 William Saunders, Girish Sastry, Andreas Stuhlmueller, Owain Evans

We formalize human intervention for RL and show how to reduce the human labor required by training a supervised learner to imitate the human's intervention decisions.

Atari Games reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.