Finding Eulerian Tours in Mazes Using a Memory-Augmented Fixed Policy Function
- 1 September 2023
- book chapter
- Published by Springer Nature
- p. 322-339
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- Comparing exploration strategies for Q-learning in random stochastic mazes2016
- Hierarchical Clustering2016
- Human-level control through deep reinforcement learningNature, 2015
- Modelling and Characterization of a Maze-Solving Mobile Robot Using Wall Follower AlgorithmApplied Mechanics and Materials, 2013
- Fast nearest neighbor retrieval for bregman divergences2008
- Efficient Learning in Cellular Simultaneous Recurrent Neural Networks - The Case of Maze Navigation Problem2007
- Solving Deep Memory POMDPs with Recurrent Policy Gradients2007
- A note on state-space decomposition methods for analyzing stochastic flow networksIEEE Transactions on Reliability, 1995
- A theory for memory-based learning1992
- Learning representations by back-propagating errorsNature, 1986