Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning

28 June 2022

Papers citing "Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning"

8 / 8 papers shown

Title
What Matters in Hierarchical Search for Combinatorial Reasoning Problems? Michał Zawalski Gracjan Góral Michał Tyrolski Emilia Wisnios Franciszek Budrowski Marek Cygan Łukasz Kuciński Piotr Miłoś 68 0 0 05 Jun 2024
Solving Sokoban with forward-backward reinforcement learning Yaron Shoham G. Elidan OffRL 92 6 0 05 May 2021
Policy-Guided Heuristic Search with Guarantees Laurent Orseau Levi H. S. Lelis 59 28 0 21 Mar 2021
Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning Dieqiao Feng Carla P. Gomes B. Selman LRM 28 23 0 04 Jun 2020
Predictive Uncertainty Estimation via Prior Networks A. Malinin Mark Gales UD BDL EDL UQCV PER 186 920 0 28 Feb 2018
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm David Silver Thomas Hubert Julian Schrittwieser Ioannis Antonoglou Matthew Lai ... D. Kumaran T. Graepel Timothy Lillicrap Karen Simonyan Demis Hassabis 143 1,775 0 05 Dec 2017
Snapshot Ensembles: Train 1, get M for free Gao Huang Yixuan Li Geoff Pleiss Zhuang Liu John E. Hopcroft Kilian Q. Weinberger OOD FedML UQCV 125 951 0 01 Apr 2017
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 821 9,318 0 06 Jun 2015