conference

PcLast: Discovering Plannable Continuous Latent States

Goal-conditioned planning benefits from learned low-dimensional representations of rich, high-dimensional observations. While compact …

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

Re-understanding finite-state representations of recurrent policy networks

We introduce an approach for understanding control policies represented as recurrent neural networks. Recent work has approached this …

Mohamad H Danesh, Anurag Koul, Alan Fern, Saeed Khorram

Explainable reinforcement learning via reward decomposition

We study reward decomposition for explaining the decisions of reinforcement learning (RL) agents. The approach decomposes rewards into …

Zoe Juozapaitis, Anurag Koul, Alan Fern, Martin Erwig, Finale Doshi-Velez

Learning finite state representations of recurrent policy networks

Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation …

Anurag Koul, Sam Greydanus, Alan Fern

Visualizing and Understanding Atari Agents

While deep reinforcement learning (deep RL) agents are effective at maximizing rewards, it is often unclear what strategies they use to …

Samuel Greydanus, Anurag Koul, Jonathan Dodge, Alan Fern