Publications

Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan Molu, Miro Dudik, John Langford, Alex Lamb (2023). PcLast: Discovering Plannable Continuous Latent States. Arxiv.

Anurag Koul, Mariano Phielipp, Alan Fern (2022). Offline Policy Comparison with Confidence: Benchmarks and Baselines. DRL Workshop, ICLR.

PDF Cite Poster Slides Docs

Mohamad H Danesh, Anurag Koul, Alan Fern, Saeed Khorram (2021). Re-understanding finite-state representations of recurrent policy networks. ICML.

Anurag Koul, Varun V Kumar, Alan Fern, Somdeb Majumdar (2020). Dream and search to control: Latent space planning for continuous control. DRL Workshop, ICLR.

PDF Cite Code Poster Slides

Zoe Juozapaitis, Anurag Koul, Alan Fern, Martin Erwig, Finale Doshi-Velez (2019). Explainable reinforcement learning via reward decomposition. IJCAI.

Anurag Koul, Sam Greydanus, Alan Fern (2018). Learning finite state representations of recurrent policy networks. ICLR.

PDF Cite Code Poster Slides

Martin Erwig, Alan Fern, Magesh Murali, Anurag Koul (2018). Explaining deep adaptive programs via reward decomposition. IJCAI/ECAI workshop on XAI.

PDF Cite Poster

Samuel Greydanus, Anurag Koul, Jonathan Dodge, Alan Fern (2017). Visualizing and Understanding Atari Agents. ICML.