117 citations · 183 across the 10 of their papers we have counts for
3 papers · 1 filter
AI Safety Gridworlds
Jan Leike, Miljan Martic, Victoria Krakovna +5
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side…
A Game-Theoretic Analysis of the Off-Switch Game
Tobias Wängberg, Mikael Böörs, Elliot Catt +2
The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human. In the original paper by Hadfield-Menell et al. (2016), the analysis is not fu…
Count-Based Exploration in Feature Space for Reinforcement Learning
Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt +1
We introduce a new count-based optimistic exploration algorithm for Reinforcement Learning (RL) that is feasible in environments with high-dimensional state-action spaces. The succ…