RE-EVALUATE: Reproducibility in Evaluating Reinforcement Learning Algorithms

By Khimya Khetarpal, Zafarali Ahmed, Andre Cianflone, Riashat Islam, Joelle Pineau. 2018

29 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. Timothée Lesort
2. Oleksiy Ostapenko
3. Massimo Caccia
4. Pau Rodr'iguez L'opez
5. Irina Rish
6. Sergey Levine
7. Matthew Riemer
8. Lucas Caccia

Citations in the corpus

• Sequoia: A Software Framework to Unify Continual Learning Research (2021, background): “To add to this, continual reinforcement learning (CRL) poses further challenges in evaluation due to the lack of a clear distinction between training and testing phases (Khetarpal et al., 2018).”
• Understanding the impact of entropy on policy optimization (2018, methodology): “Our technique is closely related to Li et al. (2018b) who used random directions for 2D interpolations, except that we interpolate in many more directions to summarize how the objective function changes locally.”