112 citations · 228 across the 11 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.AI2017★ 112 cited
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
William Saunders, Girish Sastry, Andreas Stuhlmueller +1
AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they haven't yet learned to a…
cs.LG2017★ 22 cited
Agent-Agnostic Human-in-the-Loop Reinforcement Learning
David Abel, John Salvatier, Andreas Stuhlmüller +1
Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to l…