Objective Robustness in Deep Reinforcement Learning

By Jack Koch, Lauro Langosco di Langosco, Jacob Pfau, J. Le, Lee D. Sharkey. 2021

16 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Jacob Steinhardt
2. Leo Gao
3. Nicholas Carlini
4. Dan Hendrycks
5. John Schulman
6. Sergey Levine
7. Pieter Abbeel
8. Chelsea Finn

Citations in the corpus

• GPT-NeoX-20B: An Open-Source Autoregressive Language Model (2022, background): “Being able to interpret and inspect the detailed inner workings of trained models would be a powerful tool to ensure models are optimizing for the goals we intended (Hubinger et al., 2021; Koch et al., 2021).”
• Unsolved Problems in ML Safety (2021, background): “Robustness work could also move beyond classification and consider competent errors where agents misgeneralize and execute wrong routines, such as an automated digital assistant knowing how to use a credit card to book flights, but choosing the wrong destination [100, 90].”