H Human–AI Coevolution

Entry

Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces

Garrett Warnell, Nicholas Waytowich, Vernon Lawhern, Peter Stone

Synopsis

Extends TAMER framework with deep neural networks; uses 15 minutes of human scalar feedback to train above-human performance on Atari Bowling.

Keywords

·TAMER ·interactive RL ·scalar feedback ·Atari

Open paper ↗ Report issue ↗

Related entries