Dead-ends and Secure Exploration in Reinforcement Learning

By Mehdi Fatemi, Shikhar Sharma, Harm van Seijen, Samira Ebrahimi Kahou. 2019

22 citations recorded by the source corpus.

How researchers see this paper

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

1. Paul Trichelair
2. Mehdi Fatemi
3. Romain Laroche
4. Mengyao Cao
5. Jackie Chi Kit Cheung
6. Samira Shabanian
7. Thiago D. Simão
8. Aviral Kumar

Citations in the corpus

• Safe Policy Improvement with Baseline Bootstrapping (2017, background): “, 2017), or as exploration in a hazardous environment (Schulman et al., 2015; 2017; Fatemi et al., 2019).”
• Systematic Rectification of Language Models via Dead-end Analysis (2023, methodology): “We extend the dead-end theory of Fatemi et al. (2019; 2021) from the recent reinforcement learning (RL) literature and frame the detoxification task as an auxiliary RL problem separate from LM training.”