The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning

no code implementations • 29 Sep 2021 • Dieqiao Feng, Carla P Gomes, Bart Selman

To better understanding why these approaches work we study the interplay of the policy and value networks in A\textsc{*}-based deep RL and show the surprising effectiveness of the policy network, further enhanced by the value network, as a guiding heuristic for A\textsc{*}.

reinforcement-learning Reinforcement Learning (RL)

Dataset Curation Beyond Accuracy

no code implementations • 1 Jan 2021 • Johan Bjorck, Carla P Gomes

Neural networks are known to be data-hungry, and collecting large labeled datasets is often a crucial step in deep learning deployment.

Self-Driving Cars