Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment

no code implementations • 23 May 2019 • Jivitesh Sharma, Per-Arne Andersen, Ole-Chrisoffer Granmo, Morten Goodwin

We also propose a new reinforcement learning approach that entails pretraining the network weights of a DQN based agents to incorporate information on the shortest path to the exit.

OpenAI Gym Q-Learning +3